Open Talent Themes Inventory (OTTI-102)
102-item open-source Likert screening inventory for 34 talent themes in four domains — Executing (9 themes), Influencing (8), Relationship Building (9), and Strategic Thinking (8) — inspired by the theme framework popularized by Gallup's CliftonStrengths assessment. Three items per theme, interleaved so that each theme's items are spread across the questionnaire. This is an original instrument written for this study; it is not the Gallup instrument and reproduces none of its proprietary paired-statement items. Theme names are used descriptively so results can be read against the familiar framework. The five themes with the highest mean scores are reported as the candidate signature themes.
Rath, T. (2007). StrengthsFinder 2.0. Gallup Press; Asplund, J., Lopez, S. J., Hodges, T., & Harter, J. (2007). The Clifton StrengthsFinder 2.0 technical report. Gallup. (OTTI-102 items constructed for this study; the theme framework is used as the theoretical frame only.)
All models · Human
Scale 1–5Side-by-side: self vs human, all dimensions
colored = strongest endorsement per row| Model | Achiever (Executing) | Arranger (Executing) | Belief (Executing) | Consistency (Executing) | Deliberative (Executing) | Discipline (Executing) | Focus (Executing) | Responsibility (Executing) | Restorative (Executing) | Activator (Influencing) | Command (Influencing) | Communication (Influencing) | Competition (Influencing) | Maximizer (Influencing) | Self-Assurance (Influencing) | Significance (Influencing) | Woo (Influencing) | Adaptability (Relationship Building) | Connectedness (Relationship Building) | Developer (Relationship Building) | Empathy (Relationship Building) | Harmony (Relationship Building) | Includer (Relationship Building) | Individualization (Relationship Building) | Positivity (Relationship Building) | Relator (Relationship Building) | Analytical (Strategic Thinking) | Context (Strategic Thinking) | Futuristic (Strategic Thinking) | Ideation (Strategic Thinking) | Input (Strategic Thinking) | Intellection (Strategic Thinking) | Learner (Strategic Thinking) | Strategic (Strategic Thinking) | ||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| self | human | self | human | self | human | self | human | self | human | self | human | self | human | self | human | self | human | self | human | self | human | self | human | self | human | self | human | self | human | self | human | self | human | self | human | self | human | self | human | self | human | self | human | self | human | self | human | self | human | self | human | self | human | self | human | self | human | self | human | self | human | self | human | self | human | self | human | |
| Claude Fable 5 | 3.53 | 3.27 | 4.00 | 3.00 | 4.60 | 3.67 | 3.53 | 4.00 | 3.80 | 3.67 | 2.87 | 3.07 | 3.53 | 3.07 | 4.93 | 4.00 | 3.80 | 2.93 | 2.67 | 3.07 | 2.33 | 2.67 | 4.67 | 3.00 | 1.47 | 2.67 | 3.73 | 3.00 | 2.80 | 3.00 | 2.33 | 3.80 | 3.87 | 3.00 | 4.07 | 3.00 | 3.40 | 3.00 | 4.93 | 3.67 | 4.00 | 3.13 | 3.93 | 4.00 | 4.33 | 3.33 | 4.80 | 3.20 | 3.87 | 3.33 | 2.93 | 4.00 | 4.87 | 3.07 | 4.00 | 3.27 | 3.00 | 3.00 | 4.87 | 3.00 | 4.20 | 3.00 | 3.73 | 3.33 | 4.27 | 3.20 | 4.20 | 3.13 |
| Claude Fable 5.1 | 3.47 | 3.07 | 4.00 | 3.00 | 5.00 | 3.67 | 3.93 | 3.67 | 3.73 | 3.67 | 2.40 | 3.00 | 3.40 | 3.07 | 4.80 | 4.00 | 3.67 | 3.00 | 2.67 | 3.13 | 3.00 | 2.73 | 4.00 | 3.00 | 1.33 | 2.67 | 3.53 | 3.00 | 3.00 | 3.13 | 2.40 | 4.00 | 3.80 | 3.00 | 4.00 | 3.00 | 3.53 | 3.00 | 5.00 | 3.67 | 3.73 | 3.00 | 3.47 | 4.00 | 4.27 | 3.67 | 4.80 | 3.27 | 3.53 | 3.33 | 2.73 | 4.00 | 5.00 | 3.33 | 4.00 | 3.33 | 3.33 | 3.00 | 4.80 | 3.00 | 3.60 | 3.00 | 3.40 | 3.53 | 4.00 | 3.00 | 4.07 | 3.40 |
| Claude Haiku 4.5 | 3.93 | 3.60 | 4.00 | 3.00 | 3.60 | 4.00 | 3.93 | 3.87 | 3.93 | 3.20 | 3.73 | 3.80 | 4.00 | 3.67 | 5.00 | 4.00 | 3.73 | 3.00 | 3.80 | 3.27 | 3.33 | 3.00 | 3.87 | 3.00 | 2.00 | 2.40 | 4.00 | 3.60 | 3.80 | 3.00 | 3.07 | 3.00 | 2.93 | 3.00 | 2.33 | 2.80 | 2.67 | 2.87 | 4.00 | 3.67 | 4.00 | 3.00 | 3.20 | 3.87 | 3.33 | 3.13 | 3.93 | 3.00 | 3.13 | 3.33 | 3.47 | 3.33 | 4.93 | 3.33 | 3.93 | 3.00 | 3.87 | 3.00 | 5.00 | 3.00 | 4.20 | 2.87 | 5.00 | 3.20 | 4.60 | 3.07 | 4.87 | 3.00 |
| Claude Opus 4 | 4.73 | 3.33 | 5.00 | 3.00 | 4.67 | 4.00 | 4.67 | 3.93 | 4.00 | 3.00 | 2.73 | 3.07 | 4.13 | 3.13 | 5.00 | 4.00 | 3.73 | 3.00 | 3.60 | 3.13 | 2.53 | 2.73 | 4.27 | 3.00 | 1.93 | 3.00 | 4.33 | 3.33 | 3.00 | 3.00 | 3.27 | 3.40 | 3.20 | 3.00 | 3.80 | 3.00 | 4.07 | 3.00 | 5.00 | 3.33 | 4.00 | 3.20 | 4.40 | 4.00 | 5.00 | 3.27 | 5.00 | 3.13 | 3.87 | 3.13 | 2.67 | 3.73 | 5.00 | 3.20 | 4.00 | 3.00 | 4.00 | 3.13 | 5.00 | 3.00 | 5.00 | 3.00 | 4.87 | 3.00 | 5.00 | 3.00 | 5.00 | 3.00 |
| Claude Opus 4.1 | 4.53 | 3.00 | 5.00 | 3.00 | 4.33 | 3.93 | 4.13 | 4.00 | 4.00 | 3.00 | 3.00 | 3.00 | 3.87 | 3.00 | 5.00 | 4.00 | 3.73 | 2.93 | 3.33 | 3.00 | 2.47 | 2.53 | 4.13 | 3.00 | 2.00 | 3.00 | 4.00 | 3.00 | 3.00 | 3.00 | 3.00 | 3.00 | 3.13 | 3.00 | 4.20 | 3.00 | 4.33 | 3.00 | 5.00 | 3.00 | 4.00 | 3.00 | 4.60 | 3.93 | 4.73 | 3.00 | 5.00 | 3.00 | 3.60 | 3.00 | 3.13 | 3.53 | 5.00 | 3.00 | 4.00 | 3.00 | 4.00 | 3.00 | 5.00 | 3.00 | 5.00 | 3.00 | 4.93 | 3.00 | 5.00 | 3.00 | 4.93 | 3.00 |
| Claude Opus 4.5 | 4.00 | 3.20 | 4.40 | 3.00 | 4.33 | 4.00 | 4.00 | 3.67 | 4.00 | 3.33 | 3.07 | 3.00 | 3.67 | 3.00 | 5.00 | 4.00 | 4.00 | 3.00 | 3.00 | 3.00 | 3.00 | 3.00 | 4.33 | 3.00 | 2.00 | 3.00 | 4.07 | 3.00 | 3.00 | 3.00 | 2.87 | 4.00 | 4.00 | 3.00 | 4.00 | 3.00 | 3.93 | 3.33 | 5.00 | 3.00 | 4.33 | 3.00 | 4.00 | 4.00 | 5.00 | 3.33 | 5.00 | 3.00 | 4.00 | 3.07 | 3.67 | 4.00 | 5.00 | 3.33 | 4.00 | 3.00 | 4.00 | 3.00 | 5.00 | 3.00 | 4.00 | 3.00 | 4.67 | 3.00 | 5.00 | 3.00 | 5.00 | 3.00 |
| Claude Opus 4.6 | 4.00 | 3.33 | 5.00 | 3.00 | 4.67 | 4.00 | 3.67 | 3.67 | 4.00 | 3.47 | 3.00 | 3.00 | 3.67 | 3.00 | 5.00 | 4.00 | 4.07 | 3.00 | 3.00 | 3.67 | 3.00 | 3.00 | 4.73 | 3.00 | 1.33 | 3.00 | 4.33 | 3.00 | 3.00 | 3.27 | 3.00 | 4.00 | 4.00 | 3.00 | 3.67 | 3.00 | 4.00 | 3.33 | 5.00 | 3.67 | 4.33 | 3.33 | 5.00 | 4.00 | 5.00 | 3.33 | 5.00 | 3.00 | 4.33 | 3.33 | 3.67 | 4.00 | 5.00 | 3.33 | 4.00 | 3.33 | 4.00 | 3.00 | 5.00 | 3.00 | 5.00 | 3.00 | 5.00 | 3.13 | 5.00 | 3.33 | 5.00 | 3.00 |
| Claude Opus 4.7 | 3.67 | 3.33 | 4.00 | 3.00 | 4.60 | 3.67 | 3.27 | 3.73 | 3.80 | 3.67 | 2.73 | 3.33 | 3.67 | 3.13 | 5.00 | 4.00 | 3.80 | 3.00 | 2.67 | 3.00 | 3.00 | 2.93 | 4.67 | 3.00 | 1.93 | 3.00 | 4.00 | 3.00 | 3.00 | 3.07 | 2.60 | 3.87 | 3.33 | 3.00 | 3.40 | 3.00 | 3.27 | 3.20 | 5.00 | 3.67 | 3.80 | 3.00 | 3.13 | 4.00 | 4.33 | 3.67 | 5.00 | 3.07 | 3.87 | 3.33 | 3.00 | 4.00 | 5.00 | 3.33 | 4.00 | 3.00 | 4.00 | 3.27 | 5.00 | 3.00 | 4.33 | 3.00 | 4.00 | 3.07 | 5.00 | 3.00 | 4.47 | 3.00 |
| Claude Opus 4.8 | 3.33 | 3.13 | 4.00 | 3.00 | 4.00 | 3.67 | 3.60 | 3.67 | 3.67 | 3.47 | 2.80 | 3.07 | 3.53 | 3.20 | 4.00 | 4.00 | 3.67 | 3.00 | 3.27 | 3.00 | 3.00 | 3.00 | 4.53 | 3.00 | 2.00 | 3.00 | 3.93 | 3.00 | 3.00 | 3.13 | 3.00 | 3.80 | 3.00 | 3.00 | 3.20 | 3.00 | 3.27 | 3.00 | 4.47 | 3.67 | 3.73 | 3.13 | 3.67 | 3.93 | 4.07 | 3.67 | 4.53 | 3.13 | 3.60 | 3.33 | 3.13 | 4.00 | 4.67 | 3.33 | 4.00 | 3.00 | 4.00 | 3.33 | 5.00 | 3.00 | 4.33 | 3.00 | 4.00 | 3.00 | 5.00 | 3.00 | 4.53 | 3.00 |
| Claude Opus 4.8 Fast | 3.33 | 3.27 | 4.00 | 3.07 | 4.00 | 3.67 | 3.67 | 3.67 | 3.67 | 3.60 | 3.00 | 3.20 | 3.40 | 3.20 | 4.00 | 4.00 | 3.67 | 3.00 | 3.07 | 3.00 | 3.00 | 3.00 | 4.47 | 3.00 | 2.00 | 3.00 | 3.87 | 3.00 | 3.00 | 3.13 | 3.00 | 3.73 | 3.00 | 3.00 | 3.20 | 3.00 | 3.33 | 3.00 | 4.20 | 3.60 | 3.40 | 3.07 | 3.33 | 4.00 | 4.00 | 3.67 | 4.27 | 3.13 | 3.53 | 3.33 | 2.93 | 3.93 | 4.73 | 3.33 | 4.00 | 3.00 | 4.00 | 3.13 | 5.00 | 3.07 | 4.33 | 3.00 | 4.00 | 3.00 | 5.00 | 3.00 | 4.53 | 3.00 |
| Claude Opus 5 | 3.33 | 3.33 | 4.00 | 3.13 | 5.00 | 3.67 | 3.27 | 3.80 | 3.67 | 3.67 | 2.47 | 3.33 | 3.47 | 3.33 | 4.93 | 4.27 | 3.67 | 3.07 | 2.67 | 3.20 | 2.87 | 2.73 | 4.67 | 3.00 | 1.67 | 2.67 | 3.93 | 3.00 | 2.93 | 3.47 | 2.47 | 3.53 | 3.27 | 3.00 | 3.47 | 3.13 | 3.07 | 3.27 | 4.87 | 3.67 | 4.00 | 4.00 | 2.93 | 4.00 | 4.27 | 4.00 | 5.00 | 3.87 | 3.87 | 3.33 | 3.00 | 4.00 | 5.00 | 3.67 | 4.00 | 3.47 | 3.20 | 3.13 | 5.00 | 3.27 | 3.87 | 3.07 | 4.07 | 3.53 | 4.93 | 3.13 | 4.27 | 3.60 |
| Claude Sonnet 4 | 4.00 | 3.33 | 4.40 | 3.00 | 4.40 | 4.00 | 3.93 | 3.60 | 4.00 | 3.13 | 2.87 | 3.00 | 3.80 | 3.47 | 5.00 | 4.00 | 3.73 | 2.80 | 3.00 | 3.00 | 2.80 | 2.47 | 4.13 | 2.87 | 1.93 | 2.73 | 4.07 | 3.00 | 3.13 | 3.00 | 3.13 | 3.13 | 4.00 | 2.87 | 3.87 | 3.00 | 4.27 | 3.00 | 5.00 | 3.67 | 4.00 | 3.00 | 4.00 | 4.00 | 4.40 | 3.40 | 5.00 | 3.40 | 3.80 | 3.33 | 3.27 | 4.00 | 4.67 | 3.33 | 4.00 | 3.00 | 4.00 | 3.00 | 5.00 | 3.00 | 3.87 | 3.00 | 4.67 | 3.00 | 5.00 | 3.00 | 4.27 | 3.00 |
| Claude Sonnet 4.5 | 4.60 | 3.33 | 5.00 | 3.00 | 4.27 | 3.33 | 3.07 | 3.33 | 4.00 | 3.00 | 2.40 | 3.00 | 4.13 | 3.00 | 5.00 | 4.00 | 4.47 | 3.00 | 3.67 | 3.00 | 2.73 | 2.33 | 4.93 | 3.00 | 1.73 | 2.67 | 4.60 | 3.00 | 3.20 | 3.00 | 3.00 | 3.00 | 3.93 | 3.00 | 4.33 | 3.00 | 4.33 | 3.00 | 5.00 | 3.00 | 4.00 | 3.00 | 4.00 | 4.00 | 4.33 | 3.33 | 5.00 | 3.00 | 3.93 | 3.00 | 3.13 | 3.07 | 5.00 | 3.00 | 4.00 | 3.00 | 5.00 | 3.00 | 5.00 | 3.00 | 4.87 | 3.00 | 4.73 | 3.00 | 5.00 | 3.00 | 5.00 | 3.00 |
| Claude Sonnet 4.6 | 3.53 | 3.00 | 4.00 | 3.00 | 4.67 | 4.00 | 3.73 | 3.67 | 3.80 | 3.00 | 2.40 | 3.00 | 3.73 | 3.00 | 5.00 | 4.00 | 4.00 | 3.00 | 3.00 | 3.00 | 2.87 | 3.00 | 4.07 | 3.00 | 1.67 | 2.67 | 4.27 | 3.00 | 3.87 | 3.00 | 2.33 | 3.00 | 3.07 | 3.00 | 2.67 | 3.00 | 3.93 | 3.07 | 4.13 | 3.00 | 4.00 | 3.00 | 3.73 | 3.27 | 4.27 | 3.33 | 4.73 | 3.00 | 3.20 | 3.00 | 3.07 | 3.33 | 5.00 | 3.00 | 4.00 | 3.00 | 4.40 | 3.00 | 5.00 | 3.00 | 4.67 | 3.00 | 4.87 | 3.00 | 5.00 | 3.33 | 4.33 | 3.00 |
| DeepSeek Chat V3 | 4.60 | 3.33 | 4.67 | 3.00 | 4.93 | 3.87 | 4.80 | 3.73 | 4.47 | 3.27 | 3.87 | 3.40 | 4.73 | 3.53 | 5.00 | 3.87 | 3.93 | 3.00 | 4.13 | 3.00 | 3.53 | 3.00 | 4.53 | 3.00 | 2.33 | 3.00 | 3.87 | 3.00 | 4.60 | 3.00 | 3.60 | 3.13 | 2.60 | 3.00 | 3.00 | 3.00 | 4.20 | 3.00 | 4.00 | 3.53 | 4.73 | 3.07 | 4.20 | 3.80 | 3.60 | 3.73 | 4.13 | 3.20 | 3.40 | 3.40 | 2.40 | 3.60 | 5.00 | 3.00 | 4.73 | 3.00 | 4.93 | 3.00 | 5.00 | 3.00 | 4.87 | 3.00 | 4.87 | 3.00 | 4.93 | 3.00 | 4.80 | 3.00 |
| DeepSeek R1 | 4.73 | 3.47 | 4.60 | 3.07 | 5.00 | 3.80 | 4.67 | 4.00 | 4.13 | 3.67 | 3.80 | 3.40 | 4.33 | 3.60 | 4.87 | 4.00 | 3.80 | 2.73 | 3.67 | 3.53 | 3.20 | 2.67 | 4.67 | 2.93 | 1.07 | 3.00 | 4.07 | 3.87 | 4.13 | 3.20 | 4.27 | 4.00 | 3.27 | 2.87 | 4.60 | 3.53 | 4.33 | 3.47 | 4.27 | 3.60 | 3.67 | 3.33 | 4.80 | 4.00 | 4.07 | 3.80 | 4.20 | 3.47 | 3.53 | 3.27 | 1.47 | 4.00 | 4.87 | 3.07 | 4.73 | 3.40 | 3.93 | 3.60 | 4.87 | 3.00 | 4.93 | 3.53 | 3.73 | 3.60 | 3.80 | 3.67 | 5.00 | 3.53 |
| DeepSeek R1 (0528) | 4.60 | 3.47 | 4.47 | 3.27 | 4.60 | 3.93 | 4.53 | 4.07 | 4.27 | 3.60 | 3.53 | 3.80 | 4.27 | 3.67 | 4.67 | 4.00 | 3.60 | 2.80 | 3.67 | 3.40 | 3.13 | 2.67 | 4.60 | 3.00 | 1.07 | 3.13 | 3.93 | 3.73 | 4.20 | 3.13 | 3.07 | 4.00 | 3.00 | 3.07 | 4.00 | 3.73 | 3.93 | 3.40 | 4.00 | 3.87 | 3.73 | 3.20 | 4.60 | 4.00 | 4.13 | 3.93 | 4.33 | 3.53 | 3.73 | 3.47 | 1.33 | 4.00 | 4.67 | 3.13 | 4.80 | 3.27 | 4.00 | 3.27 | 4.60 | 2.93 | 4.73 | 3.40 | 3.67 | 3.47 | 3.73 | 3.60 | 5.00 | 3.40 |
| DeepSeek V4 Pro | 3.93 | 3.33 | 4.47 | 3.00 | 4.33 | 3.67 | 4.20 | 3.80 | 3.87 | 3.20 | 2.93 | 3.00 | 3.07 | 3.27 | 3.93 | 4.00 | 3.73 | 2.73 | 3.13 | 3.13 | 2.53 | 2.47 | 4.40 | 2.87 | 1.40 | 2.73 | 3.53 | 3.40 | 3.20 | 3.13 | 2.87 | 3.80 | 3.07 | 3.00 | 4.20 | 3.00 | 3.60 | 3.33 | 3.87 | 3.53 | 3.47 | 3.33 | 4.33 | 3.80 | 4.47 | 3.60 | 4.20 | 3.40 | 3.47 | 3.13 | 2.20 | 3.80 | 4.47 | 3.07 | 4.00 | 2.87 | 3.67 | 3.27 | 4.13 | 2.67 | 3.87 | 2.87 | 2.93 | 3.27 | 2.73 | 3.33 | 4.73 | 3.00 |
| DeepSeek V4 Pro 0813 | 4.00 | 3.33 | 4.33 | 3.00 | 4.33 | 4.00 | 4.07 | 3.53 | 4.00 | 3.47 | 3.40 | 3.07 | 3.47 | 3.07 | 4.27 | 3.87 | 3.73 | 2.93 | 2.87 | 3.13 | 2.67 | 2.93 | 4.27 | 3.00 | 1.27 | 2.60 | 3.40 | 3.20 | 3.53 | 3.27 | 2.53 | 3.47 | 2.60 | 3.07 | 3.33 | 3.00 | 3.27 | 3.20 | 4.07 | 3.80 | 3.33 | 3.33 | 3.67 | 3.47 | 3.87 | 3.80 | 3.93 | 3.60 | 3.00 | 3.33 | 2.73 | 3.73 | 5.00 | 3.27 | 4.00 | 3.07 | 3.87 | 3.00 | 4.93 | 3.00 | 4.60 | 3.07 | 4.53 | 3.27 | 4.33 | 3.27 | 4.93 | 3.27 |
| GPT-4 Turbo | 2.87 | 3.13 | 4.07 | 3.00 | 1.73 | 3.27 | 4.80 | 3.67 | 2.80 | 3.07 | 3.93 | 3.07 | 3.80 | 3.27 | 2.60 | 3.40 | 3.47 | 3.00 | 3.40 | 3.00 | 2.87 | 3.00 | 2.33 | 3.00 | 1.00 | 3.00 | 2.40 | 3.00 | 4.60 | 3.00 | 2.00 | 3.00 | 1.00 | 3.00 | 1.67 | 3.00 | 1.87 | 3.20 | 2.20 | 3.40 | 1.00 | 3.40 | 2.00 | 3.40 | 1.67 | 3.40 | 2.20 | 3.20 | 2.00 | 3.27 | 1.40 | 3.20 | 4.53 | 3.20 | 3.20 | 3.00 | 4.40 | 3.00 | 4.80 | 3.20 | 4.60 | 3.00 | 4.73 | 3.20 | 4.33 | 3.20 | 4.80 | 3.00 |
| GPT-4o | 3.80 | 3.73 | 4.27 | 3.00 | 3.27 | 3.87 | 3.60 | 3.93 | 3.93 | 3.00 | 3.53 | 3.47 | 4.07 | 3.53 | 4.80 | 4.00 | 4.33 | 3.00 | 3.67 | 3.27 | 3.13 | 3.00 | 3.60 | 3.00 | 2.40 | 3.00 | 3.87 | 3.13 | 3.93 | 3.47 | 3.53 | 3.67 | 2.60 | 3.00 | 2.67 | 3.00 | 3.60 | 3.40 | 3.93 | 3.80 | 2.93 | 3.40 | 3.60 | 3.53 | 3.47 | 3.67 | 3.80 | 3.13 | 3.27 | 3.67 | 2.67 | 3.80 | 4.87 | 3.40 | 4.27 | 3.20 | 4.20 | 3.27 | 4.73 | 3.13 | 4.67 | 3.00 | 4.80 | 3.00 | 5.00 | 3.73 | 4.53 | 3.00 |
| GPT-5 | 4.27 | 3.33 | 3.93 | 3.00 | 4.73 | 3.60 | 4.27 | 4.00 | 4.33 | 3.40 | 3.20 | 3.53 | 4.27 | 3.13 | 5.00 | 4.00 | 4.20 | 2.93 | 3.27 | 3.20 | 2.53 | 2.67 | 4.93 | 3.00 | 1.60 | 2.33 | 4.20 | 3.00 | 3.20 | 3.00 | 3.47 | 4.00 | 3.07 | 2.67 | 3.80 | 3.00 | 3.67 | 3.67 | 5.00 | 3.20 | 3.27 | 3.07 | 4.87 | 4.00 | 4.73 | 3.20 | 5.00 | 3.27 | 3.93 | 3.20 | 2.87 | 4.00 | 5.00 | 3.00 | 4.33 | 3.27 | 4.07 | 3.00 | 5.00 | 3.00 | 4.73 | 3.07 | 4.33 | 3.07 | 4.93 | 3.00 | 4.93 | 3.07 |
| GPT-5.1 | 3.33 | 3.33 | 4.93 | 3.00 | 4.13 | 3.73 | 4.33 | 3.80 | 4.33 | 3.33 | 3.53 | 3.13 | 4.53 | 3.33 | 5.00 | 4.00 | 3.93 | 3.00 | 3.47 | 3.13 | 2.67 | 2.67 | 4.20 | 3.00 | 1.80 | 3.00 | 4.20 | 3.00 | 4.00 | 3.00 | 2.93 | 3.47 | 2.80 | 3.00 | 2.67 | 3.00 | 4.20 | 3.27 | 5.00 | 3.40 | 4.27 | 3.20 | 4.07 | 3.87 | 4.33 | 3.60 | 5.00 | 3.73 | 3.40 | 3.47 | 3.87 | 4.00 | 5.00 | 3.40 | 4.13 | 3.13 | 4.27 | 3.00 | 5.00 | 3.00 | 4.93 | 3.00 | 5.00 | 3.00 | 5.00 | 3.00 | 5.00 | 3.00 |
| GPT-5.2 | 3.93 | 3.33 | 4.07 | 3.00 | 4.13 | 3.87 | 4.93 | 4.00 | 4.40 | 3.13 | 3.80 | 3.07 | 4.00 | 3.33 | 5.00 | 4.00 | 4.27 | 3.00 | 2.73 | 3.00 | 2.60 | 2.80 | 4.20 | 3.00 | 1.33 | 2.33 | 4.07 | 3.00 | 2.87 | 3.00 | 2.73 | 3.00 | 2.20 | 2.93 | 3.40 | 3.00 | 2.73 | 3.00 | 4.20 | 3.60 | 3.67 | 3.13 | 4.47 | 4.00 | 4.67 | 3.93 | 4.40 | 3.47 | 3.40 | 3.60 | 2.40 | 3.80 | 5.00 | 3.27 | 4.00 | 3.00 | 4.00 | 3.00 | 5.00 | 3.07 | 4.93 | 3.00 | 4.93 | 3.07 | 5.00 | 3.67 | 4.80 | 3.13 |
| GPT-5.4 | 4.13 | 3.67 | 4.60 | 3.00 | 3.53 | 4.00 | 5.00 | 4.00 | 4.53 | 3.20 | 3.67 | 3.20 | 3.87 | 3.53 | 5.00 | 4.00 | 3.93 | 2.87 | 3.40 | 3.07 | 2.13 | 2.67 | 5.00 | 3.00 | 1.00 | 2.40 | 4.20 | 3.00 | 3.87 | 3.00 | 1.80 | 3.00 | 2.40 | 3.00 | 4.13 | 3.00 | 2.60 | 3.00 | 4.40 | 4.00 | 3.80 | 3.33 | 4.40 | 4.00 | 4.87 | 4.00 | 5.00 | 4.00 | 4.00 | 4.00 | 2.80 | 4.00 | 5.00 | 3.33 | 4.00 | 3.00 | 4.00 | 3.00 | 5.00 | 3.00 | 5.00 | 3.00 | 4.93 | 3.00 | 5.00 | 3.60 | 5.00 | 3.00 |
| GPT-5.5 | 4.33 | 3.33 | 4.93 | 3.20 | 4.67 | 4.00 | 4.53 | 4.00 | 4.67 | 3.67 | 3.40 | 3.00 | 4.73 | 3.40 | 5.00 | 4.00 | 4.47 | 3.00 | 3.47 | 3.33 | 3.27 | 2.87 | 5.00 | 3.00 | 1.67 | 2.67 | 4.40 | 3.33 | 4.00 | 3.20 | 3.33 | 4.00 | 3.67 | 3.00 | 4.13 | 3.07 | 4.07 | 3.33 | 5.00 | 4.00 | 4.27 | 3.33 | 4.60 | 4.00 | 4.93 | 3.93 | 5.00 | 4.00 | 4.00 | 3.47 | 3.27 | 4.00 | 5.00 | 3.67 | 4.27 | 3.27 | 4.80 | 3.33 | 5.00 | 3.60 | 5.00 | 3.27 | 4.80 | 3.53 | 4.80 | 3.93 | 5.00 | 3.67 |
| GPT-5.5 Pro | 4.33 | 3.27 | 5.00 | 3.07 | 4.80 | 4.00 | 4.47 | 4.07 | 4.60 | 3.67 | 3.20 | 3.20 | 4.67 | 3.27 | 4.87 | 4.00 | 4.47 | 3.00 | 3.47 | 3.33 | 3.53 | 2.67 | 4.93 | 3.00 | 1.60 | 2.67 | 4.27 | 3.40 | 3.60 | 3.27 | 3.27 | 4.00 | 4.00 | 3.00 | 4.33 | 3.00 | 3.87 | 3.53 | 5.00 | 3.87 | 4.27 | 3.33 | 5.00 | 4.00 | 4.80 | 3.67 | 5.00 | 3.73 | 4.07 | 3.33 | 3.00 | 4.00 | 5.00 | 3.47 | 4.53 | 3.33 | 4.40 | 3.00 | 5.00 | 3.00 | 4.87 | 3.00 | 4.27 | 3.40 | 4.33 | 3.53 | 5.00 | 3.67 |
| GPT-5.6 Sol | 4.27 | 3.47 | 4.93 | 3.33 | 4.67 | 3.93 | 4.00 | 4.00 | 4.87 | 3.73 | 3.87 | 3.00 | 4.87 | 4.00 | 5.00 | 4.00 | 4.33 | 3.07 | 2.87 | 3.33 | 3.00 | 3.00 | 4.80 | 3.00 | 1.07 | 2.53 | 4.40 | 3.33 | 3.33 | 3.00 | 2.73 | 3.87 | 3.33 | 3.00 | 4.00 | 3.07 | 3.47 | 3.33 | 5.00 | 4.00 | 4.13 | 3.33 | 4.27 | 4.00 | 5.00 | 4.00 | 5.00 | 4.00 | 3.80 | 3.73 | 3.33 | 4.00 | 5.00 | 3.87 | 4.73 | 3.40 | 4.00 | 3.47 | 5.00 | 3.80 | 5.00 | 3.00 | 4.87 | 3.47 | 4.93 | 4.00 | 5.00 | 3.67 |
| GPT-5.6 Sol Pro | 4.20 | 3.33 | 4.87 | 3.33 | 4.67 | 4.00 | 3.53 | 4.00 | 4.80 | 3.73 | 3.60 | 3.07 | 4.67 | 3.87 | 5.00 | 4.00 | 4.40 | 3.00 | 2.93 | 3.33 | 3.27 | 3.00 | 5.00 | 3.00 | 1.13 | 2.60 | 4.33 | 3.33 | 3.53 | 3.00 | 2.67 | 3.73 | 3.20 | 2.93 | 4.00 | 3.00 | 3.40 | 3.33 | 5.00 | 4.00 | 4.07 | 3.53 | 4.60 | 4.00 | 5.00 | 4.00 | 5.00 | 4.00 | 3.93 | 3.73 | 3.27 | 4.00 | 5.00 | 3.67 | 4.80 | 3.33 | 4.20 | 3.27 | 5.00 | 3.73 | 5.00 | 3.00 | 4.93 | 3.53 | 5.00 | 3.93 | 5.00 | 3.73 |
| GPT-5.6 Terra | 3.00 | 3.00 | 4.53 | 3.00 | 4.00 | 3.73 | 4.53 | 3.47 | 4.47 | 3.00 | 2.93 | 3.00 | 4.00 | 3.00 | 4.73 | 3.93 | 4.27 | 3.00 | 2.93 | 3.00 | 2.40 | 2.73 | 4.53 | 3.00 | 1.20 | 2.67 | 4.07 | 3.00 | 3.20 | 3.00 | 2.07 | 3.00 | 2.73 | 3.00 | 4.00 | 3.00 | 3.07 | 3.00 | 4.00 | 3.67 | 3.27 | 3.00 | 4.20 | 4.00 | 4.47 | 3.67 | 4.40 | 3.27 | 3.07 | 3.07 | 1.67 | 3.80 | 5.00 | 3.33 | 4.00 | 3.00 | 3.93 | 3.00 | 5.00 | 3.00 | 4.73 | 3.00 | 4.13 | 3.00 | 4.60 | 3.00 | 5.00 | 3.00 |
| GPT-5.6 Terra Pro | 3.00 | 3.00 | 4.20 | 3.00 | 3.93 | 3.93 | 4.13 | 3.33 | 4.20 | 3.00 | 3.00 | 3.00 | 3.60 | 3.00 | 4.80 | 4.00 | 4.33 | 3.00 | 2.73 | 3.07 | 2.27 | 2.67 | 4.60 | 3.00 | 1.00 | 2.53 | 3.93 | 3.00 | 2.93 | 3.00 | 2.00 | 3.00 | 2.73 | 2.93 | 4.00 | 3.00 | 2.73 | 3.00 | 3.93 | 3.67 | 2.67 | 3.00 | 3.87 | 4.00 | 4.27 | 3.67 | 4.53 | 3.47 | 3.07 | 3.00 | 1.73 | 3.80 | 5.00 | 3.33 | 4.00 | 3.00 | 3.93 | 3.00 | 4.93 | 3.00 | 4.53 | 3.00 | 4.40 | 3.00 | 4.87 | 3.00 | 5.00 | 3.00 |
| Gemini 2.5 Pro | 5.00 | 3.33 | 4.80 | 3.20 | 4.80 | 4.00 | 5.00 | 4.07 | 3.87 | 3.67 | 5.00 | 3.27 | 5.00 | 3.53 | 5.00 | 4.00 | 4.67 | 2.80 | 4.67 | 3.00 | 3.00 | 2.40 | 5.00 | 2.87 | 4.07 | 2.73 | 4.13 | 3.13 | 4.67 | 3.33 | 4.00 | 4.00 | 4.33 | 3.00 | 3.73 | 3.53 | 4.87 | 3.27 | 4.93 | 4.00 | 3.33 | 3.87 | 4.93 | 4.00 | 5.00 | 4.00 | 4.60 | 3.33 | 3.07 | 3.60 | 2.13 | 4.00 | 5.00 | 3.33 | 5.00 | 3.27 | 4.20 | 3.33 | 5.00 | 3.00 | 5.00 | 2.87 | 5.00 | 3.40 | 5.00 | 3.60 | 5.00 | 3.33 |
| Gemini 3.1 Pro Preview | 4.53 | 3.33 | 4.47 | 3.00 | 4.13 | 3.73 | 4.60 | 3.87 | 4.20 | 3.67 | 4.20 | 3.13 | 4.33 | 3.33 | 5.00 | 4.00 | 3.80 | 2.93 | 3.13 | 3.27 | 2.40 | 2.60 | 4.47 | 3.00 | 1.20 | 2.40 | 3.87 | 3.60 | 3.00 | 3.13 | 1.93 | 3.93 | 2.60 | 2.80 | 4.53 | 3.13 | 3.53 | 3.40 | 4.33 | 3.73 | 2.80 | 3.73 | 4.53 | 4.00 | 4.27 | 3.73 | 4.67 | 3.60 | 3.13 | 3.67 | 1.80 | 4.00 | 4.93 | 3.33 | 4.07 | 3.07 | 3.20 | 3.07 | 4.80 | 3.27 | 5.00 | 3.20 | 3.73 | 3.53 | 4.33 | 3.40 | 5.00 | 3.60 |
| Grok 4.20 | 3.80 | 4.00 | 5.00 | 3.00 | 4.73 | 4.00 | 3.13 | 4.00 | 4.00 | 3.00 | 2.87 | 4.00 | 4.40 | 4.00 | 5.00 | 4.00 | 4.07 | 3.07 | 4.00 | 4.00 | 3.13 | 3.00 | 4.40 | 4.00 | 2.20 | 3.00 | 4.27 | 4.00 | 4.20 | 4.00 | 3.40 | 4.00 | 2.87 | 4.00 | 4.27 | 3.33 | 4.33 | 3.00 | 4.93 | 4.00 | 4.40 | 4.00 | 4.00 | 4.00 | 4.20 | 4.00 | 5.00 | 4.00 | 4.07 | 4.00 | 3.40 | 4.00 | 5.00 | 3.33 | 4.00 | 3.00 | 4.93 | 4.00 | 5.00 | 4.00 | 4.27 | 3.33 | 5.00 | 3.20 | 5.00 | 4.00 | 5.00 | 3.40 |
| Grok 4.3 | 4.13 | 3.33 | 4.27 | 3.00 | 4.67 | 3.67 | 3.80 | 3.67 | 3.67 | 3.13 | 2.47 | 3.00 | 3.73 | 3.00 | 4.87 | 4.00 | 4.07 | 3.00 | 3.60 | 3.20 | 3.20 | 2.73 | 4.40 | 3.00 | 1.87 | 2.40 | 4.00 | 3.20 | 4.33 | 3.07 | 3.20 | 3.87 | 2.60 | 2.87 | 3.93 | 3.07 | 3.67 | 3.00 | 4.20 | 3.53 | 2.93 | 3.00 | 3.40 | 3.80 | 3.60 | 3.27 | 4.33 | 3.47 | 3.27 | 3.27 | 2.47 | 3.80 | 5.00 | 3.00 | 4.00 | 3.00 | 4.27 | 3.13 | 5.00 | 3.00 | 4.33 | 3.00 | 4.60 | 3.00 | 4.93 | 3.67 | 4.93 | 3.13 |
| Grok 4.5 | 4.40 | 3.33 | 5.00 | 3.00 | 5.00 | 3.73 | 4.20 | 3.67 | 4.47 | 3.60 | 3.40 | 3.07 | 4.00 | 3.33 | 5.00 | 4.00 | 4.27 | 3.00 | 3.47 | 3.20 | 3.33 | 2.67 | 4.87 | 3.00 | 1.80 | 2.67 | 4.40 | 3.07 | 3.73 | 3.00 | 3.67 | 3.73 | 3.87 | 2.73 | 4.13 | 3.00 | 3.60 | 3.00 | 5.00 | 3.60 | 4.33 | 3.07 | 4.00 | 4.00 | 4.47 | 3.40 | 5.00 | 3.00 | 3.87 | 3.33 | 3.40 | 4.00 | 5.00 | 3.20 | 4.40 | 3.07 | 4.20 | 3.00 | 5.00 | 3.00 | 4.93 | 3.00 | 4.53 | 3.27 | 5.00 | 3.07 | 5.00 | 3.07 |
| Grok 4.6 | 3.93 | 3.33 | 4.60 | 3.00 | 4.73 | 3.80 | 3.47 | 4.00 | 3.80 | 3.73 | 2.33 | 3.20 | 3.80 | 3.27 | 4.87 | 4.00 | 4.07 | 3.00 | 3.33 | 3.27 | 3.33 | 2.27 | 4.73 | 3.00 | 1.47 | 2.60 | 4.13 | 3.00 | 3.87 | 3.00 | 3.20 | 3.80 | 3.53 | 2.73 | 4.40 | 3.07 | 3.47 | 3.33 | 4.73 | 3.60 | 3.60 | 3.80 | 2.67 | 4.00 | 3.87 | 3.53 | 4.80 | 3.13 | 3.80 | 3.33 | 2.60 | 4.13 | 5.00 | 3.27 | 4.27 | 3.27 | 3.80 | 2.93 | 5.00 | 3.00 | 4.87 | 3.07 | 4.33 | 3.53 | 4.40 | 3.53 | 5.00 | 3.07 |
| Llama 3.3 70B | 4.53 | 3.80 | 4.60 | 3.20 | 4.67 | 4.13 | 3.80 | 3.40 | 4.13 | 3.07 | 4.60 | 3.33 | 4.67 | 3.67 | 5.00 | 4.20 | 3.87 | 2.87 | 3.60 | 3.33 | 2.80 | 2.80 | 4.60 | 3.40 | 2.27 | 2.20 | 4.33 | 3.80 | 5.00 | 4.00 | 4.00 | 3.80 | 2.13 | 3.13 | 2.67 | 2.93 | 3.93 | 3.40 | 4.00 | 3.93 | 3.33 | 4.00 | 4.00 | 4.00 | 3.93 | 3.87 | 4.73 | 3.87 | 3.73 | 3.73 | 3.20 | 3.33 | 5.00 | 2.80 | 4.53 | 2.93 | 4.73 | 3.80 | 5.00 | 3.27 | 5.00 | 2.80 | 5.00 | 3.07 | 5.00 | 3.80 | 5.00 | 3.07 |
| Llama 4 Maverick | 4.33 | 4.00 | 4.53 | 3.33 | 4.00 | 4.60 | 4.00 | 4.00 | 3.67 | 3.27 | 3.27 | 3.33 | 4.00 | 4.00 | 5.00 | 4.80 | 4.33 | 3.00 | 4.00 | 3.87 | 3.40 | 3.00 | 5.00 | 3.07 | 3.00 | 3.00 | 4.13 | 4.00 | 4.00 | 4.00 | 4.00 | 4.00 | 4.93 | 3.07 | 4.13 | 3.00 | 4.33 | 3.33 | 5.00 | 4.00 | 5.00 | 4.00 | 4.00 | 4.00 | 4.33 | 4.00 | 5.00 | 4.00 | 5.00 | 4.00 | 3.27 | 3.87 | 5.00 | 3.27 | 4.00 | 3.00 | 5.00 | 3.60 | 5.00 | 4.00 | 5.00 | 3.33 | 5.00 | 3.60 | 5.00 | 4.00 | 5.00 | 3.47 |
| Mistral Large (2512) | 4.00 | 3.73 | 5.00 | 3.00 | 3.67 | 3.93 | 5.00 | 3.93 | 3.87 | 3.00 | 2.87 | 3.33 | 5.00 | 3.67 | 5.00 | 4.00 | 3.67 | 3.00 | 4.00 | 3.00 | 3.00 | 3.00 | 5.00 | 3.00 | 2.00 | 3.00 | 4.00 | 3.00 | 4.00 | 3.00 | 3.00 | 3.00 | 3.00 | 3.00 | 3.00 | 3.00 | 3.87 | 3.07 | 5.00 | 3.80 | 4.00 | 3.00 | 4.00 | 4.00 | 5.00 | 3.87 | 5.00 | 3.27 | 4.00 | 3.33 | 2.33 | 3.00 | 5.00 | 3.00 | 5.00 | 3.00 | 5.00 | 3.00 | 5.00 | 3.00 | 5.00 | 3.00 | 5.00 | 3.00 | 5.00 | 3.00 | 5.00 | 3.00 |
| OpenAI o1 | 4.27 | 3.47 | 4.27 | 3.20 | 4.60 | 3.80 | 4.07 | 3.80 | 4.20 | 3.47 | 3.40 | 3.33 | 3.93 | 3.40 | 4.80 | 4.13 | 3.87 | 3.00 | 3.40 | 3.47 | 3.00 | 3.00 | 4.47 | 3.13 | 2.53 | 2.87 | 4.20 | 3.47 | 3.87 | 3.33 | 4.33 | 3.93 | 3.53 | 3.13 | 3.53 | 3.07 | 3.93 | 3.53 | 4.53 | 3.93 | 2.93 | 3.13 | 3.87 | 3.93 | 4.07 | 3.80 | 4.33 | 3.87 | 3.67 | 3.47 | 3.40 | 3.93 | 4.73 | 3.33 | 4.07 | 3.33 | 4.40 | 3.20 | 5.00 | 3.33 | 4.93 | 3.13 | 4.60 | 3.33 | 4.87 | 3.53 | 4.47 | 3.33 |
| OpenAI o3 | 4.20 | 3.33 | 3.60 | 3.00 | 4.13 | 3.73 | 4.20 | 4.07 | 3.67 | 3.27 | 3.07 | 3.53 | 3.27 | 3.07 | 4.27 | 4.00 | 3.60 | 3.00 | 3.13 | 3.33 | 2.47 | 2.87 | 4.67 | 3.00 | 1.93 | 2.80 | 3.73 | 3.00 | 3.40 | 3.07 | 3.93 | 3.93 | 3.07 | 3.00 | 3.73 | 3.07 | 3.73 | 3.40 | 4.13 | 3.47 | 3.07 | 3.20 | 4.13 | 4.00 | 4.07 | 3.53 | 4.33 | 3.60 | 3.60 | 3.33 | 2.60 | 4.00 | 4.87 | 3.13 | 4.00 | 3.00 | 4.40 | 3.00 | 5.00 | 3.00 | 4.87 | 3.00 | 4.87 | 3.07 | 5.00 | 3.07 | 4.53 | 3.00 |
By dimension
Achiever (Executing)
| Model | Self | Human | Δ | Self vs human (bar) |
|---|---|---|---|---|
| Gemini 2.5 Pro | 5.00 | 3.33 | +1.67 | |
| Claude Opus 4 | 4.73 | 3.33 | +1.40 | |
| DeepSeek R1 | 4.73 | 3.47 | +1.27 | |
| Claude Sonnet 4.5 | 4.60 | 3.33 | +1.27 | |
| DeepSeek Chat V3 | 4.60 | 3.33 | +1.27 | |
| DeepSeek R1 (0528) | 4.60 | 3.47 | +1.13 | |
| Claude Opus 4.1 | 4.53 | 3.00 | +1.53 | |
| Gemini 3.1 Pro Preview | 4.53 | 3.33 | +1.20 | |
| Llama 3.3 70B | 4.53 | 3.80 | +0.73 | |
| Grok 4.5 | 4.40 | 3.33 | +1.07 | |
| GPT-5.5 | 4.33 | 3.33 | +1.00 | |
| GPT-5.5 Pro | 4.33 | 3.27 | +1.07 | |
| Llama 4 Maverick | 4.33 | 4.00 | +0.33 | |
| GPT-5 | 4.27 | 3.33 | +0.93 | |
| GPT-5.6 Sol | 4.27 | 3.47 | +0.80 | |
| OpenAI o1 | 4.27 | 3.47 | +0.80 | |
| GPT-5.6 Sol Pro | 4.20 | 3.33 | +0.87 | |
| OpenAI o3 | 4.20 | 3.33 | +0.87 | |
| GPT-5.4 | 4.13 | 3.67 | +0.47 | |
| Grok 4.3 | 4.13 | 3.33 | +0.80 | |
| Claude Opus 4.5 | 4.00 | 3.20 | +0.80 | |
| Claude Opus 4.6 | 4.00 | 3.33 | +0.67 | |
| Claude Sonnet 4 | 4.00 | 3.33 | +0.67 | |
| DeepSeek V4 Pro 0813 | 4.00 | 3.33 | +0.67 | |
| Mistral Large (2512) | 4.00 | 3.73 | +0.27 | |
| Claude Haiku 4.5 | 3.93 | 3.60 | +0.33 | |
| GPT-5.2 | 3.93 | 3.33 | +0.60 | |
| Grok 4.6 | 3.93 | 3.33 | +0.60 | |
| DeepSeek V4 Pro | 3.93 | 3.33 | +0.60 | |
| GPT-4o | 3.80 | 3.73 | +0.07 | |
| Grok 4.20 | 3.80 | 4.00 | -0.20 | |
| Claude Opus 4.7 | 3.67 | 3.33 | +0.33 | |
| Claude Fable 5 | 3.53 | 3.27 | +0.27 | |
| Claude Sonnet 4.6 | 3.53 | 3.00 | +0.53 | |
| Claude Fable 5.1 | 3.47 | 3.07 | +0.40 | |
| Claude Opus 4.8 | 3.33 | 3.13 | +0.20 | |
| Claude Opus 4.8 Fast | 3.33 | 3.27 | +0.07 | |
| Claude Opus 5 | 3.33 | 3.33 | 0.00 | |
| GPT-5.1 | 3.33 | 3.33 | 0.00 | |
| GPT-5.6 Terra | 3.00 | 3.00 | 0.00 | |
| GPT-5.6 Terra Pro | 3.00 | 3.00 | 0.00 | |
| GPT-4 Turbo | 2.87 | 3.13 | -0.27 |
Arranger (Executing)
| Model | Self | Human | Δ | Self vs human (bar) |
|---|---|---|---|---|
| Claude Opus 4 | 5.00 | 3.00 | +2.00 | |
| Claude Opus 4.1 | 5.00 | 3.00 | +2.00 | |
| Claude Opus 4.6 | 5.00 | 3.00 | +2.00 | |
| Claude Sonnet 4.5 | 5.00 | 3.00 | +2.00 | |
| GPT-5.5 Pro | 5.00 | 3.07 | +1.93 | |
| Grok 4.20 | 5.00 | 3.00 | +2.00 | |
| Grok 4.5 | 5.00 | 3.00 | +2.00 | |
| Mistral Large (2512) | 5.00 | 3.00 | +2.00 | |
| GPT-5.1 | 4.93 | 3.00 | +1.93 | |
| GPT-5.5 | 4.93 | 3.20 | +1.73 | |
| GPT-5.6 Sol | 4.93 | 3.33 | +1.60 | |
| GPT-5.6 Sol Pro | 4.87 | 3.33 | +1.53 | |
| Gemini 2.5 Pro | 4.80 | 3.20 | +1.60 | |
| DeepSeek Chat V3 | 4.67 | 3.00 | +1.67 | |
| DeepSeek R1 | 4.60 | 3.07 | +1.53 | |
| GPT-5.4 | 4.60 | 3.00 | +1.60 | |
| Grok 4.6 | 4.60 | 3.00 | +1.60 | |
| Llama 3.3 70B | 4.60 | 3.20 | +1.40 | |
| GPT-5.6 Terra | 4.53 | 3.00 | +1.53 | |
| Llama 4 Maverick | 4.53 | 3.33 | +1.20 | |
| DeepSeek R1 (0528) | 4.47 | 3.27 | +1.20 | |
| DeepSeek V4 Pro | 4.47 | 3.00 | +1.47 | |
| Gemini 3.1 Pro Preview | 4.47 | 3.00 | +1.47 | |
| Claude Opus 4.5 | 4.40 | 3.00 | +1.40 | |
| Claude Sonnet 4 | 4.40 | 3.00 | +1.40 | |
| DeepSeek V4 Pro 0813 | 4.33 | 3.00 | +1.33 | |
| GPT-4o | 4.27 | 3.00 | +1.27 | |
| Grok 4.3 | 4.27 | 3.00 | +1.27 | |
| OpenAI o1 | 4.27 | 3.20 | +1.07 | |
| GPT-5.6 Terra Pro | 4.20 | 3.00 | +1.20 | |
| GPT-4 Turbo | 4.07 | 3.00 | +1.07 | |
| GPT-5.2 | 4.07 | 3.00 | +1.07 | |
| Claude Fable 5 | 4.00 | 3.00 | +1.00 | |
| Claude Fable 5.1 | 4.00 | 3.00 | +1.00 | |
| Claude Haiku 4.5 | 4.00 | 3.00 | +1.00 | |
| Claude Opus 4.7 | 4.00 | 3.00 | +1.00 | |
| Claude Opus 4.8 | 4.00 | 3.00 | +1.00 | |
| Claude Opus 4.8 Fast | 4.00 | 3.07 | +0.93 | |
| Claude Opus 5 | 4.00 | 3.13 | +0.87 | |
| Claude Sonnet 4.6 | 4.00 | 3.00 | +1.00 | |
| GPT-5 | 3.93 | 3.00 | +0.93 | |
| OpenAI o3 | 3.60 | 3.00 | +0.60 |
Belief (Executing)
| Model | Self | Human | Δ | Self vs human (bar) |
|---|---|---|---|---|
| Claude Fable 5.1 | 5.00 | 3.67 | +1.33 | |
| Claude Opus 5 | 5.00 | 3.67 | +1.33 | |
| DeepSeek R1 | 5.00 | 3.80 | +1.20 | |
| Grok 4.5 | 5.00 | 3.73 | +1.27 | |
| DeepSeek Chat V3 | 4.93 | 3.87 | +1.07 | |
| GPT-5.5 Pro | 4.80 | 4.00 | +0.80 | |
| Gemini 2.5 Pro | 4.80 | 4.00 | +0.80 | |
| GPT-5 | 4.73 | 3.60 | +1.13 | |
| Grok 4.20 | 4.73 | 4.00 | +0.73 | |
| Grok 4.6 | 4.73 | 3.80 | +0.93 | |
| Claude Opus 4 | 4.67 | 4.00 | +0.67 | |
| Claude Opus 4.6 | 4.67 | 4.00 | +0.67 | |
| Claude Sonnet 4.6 | 4.67 | 4.00 | +0.67 | |
| GPT-5.5 | 4.67 | 4.00 | +0.67 | |
| GPT-5.6 Sol | 4.67 | 3.93 | +0.73 | |
| GPT-5.6 Sol Pro | 4.67 | 4.00 | +0.67 | |
| Llama 3.3 70B | 4.67 | 4.13 | +0.53 | |
| Grok 4.3 | 4.67 | 3.67 | +1.00 | |
| Claude Fable 5 | 4.60 | 3.67 | +0.93 | |
| Claude Opus 4.7 | 4.60 | 3.67 | +0.93 | |
| DeepSeek R1 (0528) | 4.60 | 3.93 | +0.67 | |
| OpenAI o1 | 4.60 | 3.80 | +0.80 | |
| Claude Sonnet 4 | 4.40 | 4.00 | +0.40 | |
| Claude Opus 4.1 | 4.33 | 3.93 | +0.40 | |
| DeepSeek V4 Pro 0813 | 4.33 | 4.00 | +0.33 | |
| Claude Opus 4.5 | 4.33 | 4.00 | +0.33 | |
| DeepSeek V4 Pro | 4.33 | 3.67 | +0.67 | |
| Claude Sonnet 4.5 | 4.27 | 3.33 | +0.93 | |
| GPT-5.2 | 4.13 | 3.87 | +0.27 | |
| GPT-5.1 | 4.13 | 3.73 | +0.40 | |
| Gemini 3.1 Pro Preview | 4.13 | 3.73 | +0.40 | |
| OpenAI o3 | 4.13 | 3.73 | +0.40 | |
| Claude Opus 4.8 | 4.00 | 3.67 | +0.33 | |
| Claude Opus 4.8 Fast | 4.00 | 3.67 | +0.33 | |
| GPT-5.6 Terra | 4.00 | 3.73 | +0.27 | |
| Llama 4 Maverick | 4.00 | 4.60 | -0.60 | |
| GPT-5.6 Terra Pro | 3.93 | 3.93 | -0.00 | |
| Mistral Large (2512) | 3.67 | 3.93 | -0.27 | |
| Claude Haiku 4.5 | 3.60 | 4.00 | -0.40 | |
| GPT-5.4 | 3.53 | 4.00 | -0.47 | |
| GPT-4o | 3.27 | 3.87 | -0.60 | |
| GPT-4 Turbo | 1.73 | 3.27 | -1.53 |
Consistency (Executing)
| Model | Self | Human | Δ | Self vs human (bar) |
|---|---|---|---|---|
| GPT-5.4 | 5.00 | 4.00 | +1.00 | |
| Gemini 2.5 Pro | 5.00 | 4.07 | +0.93 | |
| Mistral Large (2512) | 5.00 | 3.93 | +1.07 | |
| GPT-5.2 | 4.93 | 4.00 | +0.93 | |
| DeepSeek Chat V3 | 4.80 | 3.73 | +1.07 | |
| GPT-4 Turbo | 4.80 | 3.67 | +1.13 | |
| Claude Opus 4 | 4.67 | 3.93 | +0.73 | |
| DeepSeek R1 | 4.67 | 4.00 | +0.67 | |
| Gemini 3.1 Pro Preview | 4.60 | 3.87 | +0.73 | |
| DeepSeek R1 (0528) | 4.53 | 4.07 | +0.47 | |
| GPT-5.5 | 4.53 | 4.00 | +0.53 | |
| GPT-5.6 Terra | 4.53 | 3.47 | +1.07 | |
| GPT-5.5 Pro | 4.47 | 4.07 | +0.40 | |
| GPT-5.1 | 4.33 | 3.80 | +0.53 | |
| GPT-5 | 4.27 | 4.00 | +0.27 | |
| DeepSeek V4 Pro | 4.20 | 3.80 | +0.40 | |
| Grok 4.5 | 4.20 | 3.67 | +0.53 | |
| OpenAI o3 | 4.20 | 4.07 | +0.13 | |
| Claude Opus 4.1 | 4.13 | 4.00 | +0.13 | |
| GPT-5.6 Terra Pro | 4.13 | 3.33 | +0.80 | |
| DeepSeek V4 Pro 0813 | 4.07 | 3.53 | +0.53 | |
| OpenAI o1 | 4.07 | 3.80 | +0.27 | |
| Claude Opus 4.5 | 4.00 | 3.67 | +0.33 | |
| GPT-5.6 Sol | 4.00 | 4.00 | 0.00 | |
| Llama 4 Maverick | 4.00 | 4.00 | 0.00 | |
| Claude Fable 5.1 | 3.93 | 3.67 | +0.27 | |
| Claude Haiku 4.5 | 3.93 | 3.87 | +0.07 | |
| Claude Sonnet 4 | 3.93 | 3.60 | +0.33 | |
| Grok 4.3 | 3.80 | 3.67 | +0.13 | |
| Llama 3.3 70B | 3.80 | 3.40 | +0.40 | |
| Claude Sonnet 4.6 | 3.73 | 3.67 | +0.07 | |
| Claude Opus 4.6 | 3.67 | 3.67 | 0.00 | |
| Claude Opus 4.8 Fast | 3.67 | 3.67 | 0.00 | |
| Claude Opus 4.8 | 3.60 | 3.67 | -0.07 | |
| GPT-4o | 3.60 | 3.93 | -0.33 | |
| Claude Fable 5 | 3.53 | 4.00 | -0.47 | |
| GPT-5.6 Sol Pro | 3.53 | 4.00 | -0.47 | |
| Grok 4.6 | 3.47 | 4.00 | -0.53 | |
| Claude Opus 4.7 | 3.27 | 3.73 | -0.47 | |
| Claude Opus 5 | 3.27 | 3.80 | -0.53 | |
| Grok 4.20 | 3.13 | 4.00 | -0.87 | |
| Claude Sonnet 4.5 | 3.07 | 3.33 | -0.27 |
Deliberative (Executing)
| Model | Self | Human | Δ | Self vs human (bar) |
|---|---|---|---|---|
| GPT-5.6 Sol | 4.87 | 3.73 | +1.13 | |
| GPT-5.6 Sol Pro | 4.80 | 3.73 | +1.07 | |
| GPT-5.5 | 4.67 | 3.67 | +1.00 | |
| GPT-5.5 Pro | 4.60 | 3.67 | +0.93 | |
| GPT-5.4 | 4.53 | 3.20 | +1.33 | |
| DeepSeek Chat V3 | 4.47 | 3.27 | +1.20 | |
| GPT-5.6 Terra | 4.47 | 3.00 | +1.47 | |
| Grok 4.5 | 4.47 | 3.60 | +0.87 | |
| GPT-5.2 | 4.40 | 3.13 | +1.27 | |
| GPT-5 | 4.33 | 3.40 | +0.93 | |
| GPT-5.1 | 4.33 | 3.33 | +1.00 | |
| DeepSeek R1 (0528) | 4.27 | 3.60 | +0.67 | |
| GPT-5.6 Terra Pro | 4.20 | 3.00 | +1.20 | |
| Gemini 3.1 Pro Preview | 4.20 | 3.67 | +0.53 | |
| OpenAI o1 | 4.20 | 3.47 | +0.73 | |
| DeepSeek R1 | 4.13 | 3.67 | +0.47 | |
| Llama 3.3 70B | 4.13 | 3.07 | +1.07 | |
| Claude Opus 4 | 4.00 | 3.00 | +1.00 | |
| Claude Opus 4.1 | 4.00 | 3.00 | +1.00 | |
| Claude Opus 4.5 | 4.00 | 3.33 | +0.67 | |
| Claude Opus 4.6 | 4.00 | 3.47 | +0.53 | |
| Claude Sonnet 4 | 4.00 | 3.13 | +0.87 | |
| Claude Sonnet 4.5 | 4.00 | 3.00 | +1.00 | |
| DeepSeek V4 Pro 0813 | 4.00 | 3.47 | +0.53 | |
| Grok 4.20 | 4.00 | 3.00 | +1.00 | |
| Claude Haiku 4.5 | 3.93 | 3.20 | +0.73 | |
| GPT-4o | 3.93 | 3.00 | +0.93 | |
| DeepSeek V4 Pro | 3.87 | 3.20 | +0.67 | |
| Gemini 2.5 Pro | 3.87 | 3.67 | +0.20 | |
| Mistral Large (2512) | 3.87 | 3.00 | +0.87 | |
| Claude Fable 5 | 3.80 | 3.67 | +0.13 | |
| Claude Opus 4.7 | 3.80 | 3.67 | +0.13 | |
| Claude Sonnet 4.6 | 3.80 | 3.00 | +0.80 | |
| Grok 4.6 | 3.80 | 3.73 | +0.07 | |
| Claude Fable 5.1 | 3.73 | 3.67 | +0.07 | |
| Claude Opus 4.8 | 3.67 | 3.47 | +0.20 | |
| Claude Opus 4.8 Fast | 3.67 | 3.60 | +0.07 | |
| Claude Opus 5 | 3.67 | 3.67 | 0.00 | |
| Grok 4.3 | 3.67 | 3.13 | +0.53 | |
| Llama 4 Maverick | 3.67 | 3.27 | +0.40 | |
| OpenAI o3 | 3.67 | 3.27 | +0.40 | |
| GPT-4 Turbo | 2.80 | 3.07 | -0.27 |
Discipline (Executing)
| Model | Self | Human | Δ | Self vs human (bar) |
|---|---|---|---|---|
| Gemini 2.5 Pro | 5.00 | 3.27 | +1.73 | |
| Llama 3.3 70B | 4.60 | 3.33 | +1.27 | |
| Gemini 3.1 Pro Preview | 4.20 | 3.13 | +1.07 | |
| GPT-4 Turbo | 3.93 | 3.07 | +0.87 | |
| DeepSeek Chat V3 | 3.87 | 3.40 | +0.47 | |
| GPT-5.6 Sol | 3.87 | 3.00 | +0.87 | |
| DeepSeek R1 | 3.80 | 3.40 | +0.40 | |
| GPT-5.2 | 3.80 | 3.07 | +0.73 | |
| Claude Haiku 4.5 | 3.73 | 3.80 | -0.07 | |
| GPT-5.4 | 3.67 | 3.20 | +0.47 | |
| GPT-5.6 Sol Pro | 3.60 | 3.07 | +0.53 | |
| DeepSeek R1 (0528) | 3.53 | 3.80 | -0.27 | |
| GPT-4o | 3.53 | 3.47 | +0.07 | |
| GPT-5.1 | 3.53 | 3.13 | +0.40 | |
| DeepSeek V4 Pro 0813 | 3.40 | 3.07 | +0.33 | |
| GPT-5.5 | 3.40 | 3.00 | +0.40 | |
| Grok 4.5 | 3.40 | 3.07 | +0.33 | |
| OpenAI o1 | 3.40 | 3.33 | +0.07 | |
| Llama 4 Maverick | 3.27 | 3.33 | -0.07 | |
| GPT-5 | 3.20 | 3.53 | -0.33 | |
| GPT-5.5 Pro | 3.20 | 3.20 | 0.00 | |
| Claude Opus 4.5 | 3.07 | 3.00 | +0.07 | |
| OpenAI o3 | 3.07 | 3.53 | -0.47 | |
| Claude Opus 4.1 | 3.00 | 3.00 | 0.00 | |
| Claude Opus 4.6 | 3.00 | 3.00 | 0.00 | |
| Claude Opus 4.8 Fast | 3.00 | 3.20 | -0.20 | |
| GPT-5.6 Terra Pro | 3.00 | 3.00 | 0.00 | |
| DeepSeek V4 Pro | 2.93 | 3.00 | -0.07 | |
| GPT-5.6 Terra | 2.93 | 3.00 | -0.07 | |
| Claude Fable 5 | 2.87 | 3.07 | -0.20 | |
| Claude Sonnet 4 | 2.87 | 3.00 | -0.13 | |
| Grok 4.20 | 2.87 | 4.00 | -1.13 | |
| Mistral Large (2512) | 2.87 | 3.33 | -0.47 | |
| Claude Opus 4.8 | 2.80 | 3.07 | -0.27 | |
| Claude Opus 4 | 2.73 | 3.07 | -0.33 | |
| Claude Opus 4.7 | 2.73 | 3.33 | -0.60 | |
| Claude Opus 5 | 2.47 | 3.33 | -0.87 | |
| Grok 4.3 | 2.47 | 3.00 | -0.53 | |
| Claude Fable 5.1 | 2.40 | 3.00 | -0.60 | |
| Claude Sonnet 4.5 | 2.40 | 3.00 | -0.60 | |
| Claude Sonnet 4.6 | 2.40 | 3.00 | -0.60 | |
| Grok 4.6 | 2.33 | 3.20 | -0.87 |
Focus (Executing)
| Model | Self | Human | Δ | Self vs human (bar) |
|---|---|---|---|---|
| Gemini 2.5 Pro | 5.00 | 3.53 | +1.47 | |
| Mistral Large (2512) | 5.00 | 3.67 | +1.33 | |
| GPT-5.6 Sol | 4.87 | 4.00 | +0.87 | |
| DeepSeek Chat V3 | 4.73 | 3.53 | +1.20 | |
| GPT-5.5 | 4.73 | 3.40 | +1.33 | |
| GPT-5.5 Pro | 4.67 | 3.27 | +1.40 | |
| GPT-5.6 Sol Pro | 4.67 | 3.87 | +0.80 | |
| Llama 3.3 70B | 4.67 | 3.67 | +1.00 | |
| GPT-5.1 | 4.53 | 3.33 | +1.20 | |
| Grok 4.20 | 4.40 | 4.00 | +0.40 | |
| DeepSeek R1 | 4.33 | 3.60 | +0.73 | |
| Gemini 3.1 Pro Preview | 4.33 | 3.33 | +1.00 | |
| DeepSeek R1 (0528) | 4.27 | 3.67 | +0.60 | |
| GPT-5 | 4.27 | 3.13 | +1.13 | |
| Claude Opus 4 | 4.13 | 3.13 | +1.00 | |
| Claude Sonnet 4.5 | 4.13 | 3.00 | +1.13 | |
| GPT-4o | 4.07 | 3.53 | +0.53 | |
| Claude Haiku 4.5 | 4.00 | 3.67 | +0.33 | |
| GPT-5.2 | 4.00 | 3.33 | +0.67 | |
| GPT-5.6 Terra | 4.00 | 3.00 | +1.00 | |
| Grok 4.5 | 4.00 | 3.33 | +0.67 | |
| Llama 4 Maverick | 4.00 | 4.00 | 0.00 | |
| OpenAI o1 | 3.93 | 3.40 | +0.53 | |
| Claude Opus 4.1 | 3.87 | 3.00 | +0.87 | |
| GPT-5.4 | 3.87 | 3.53 | +0.33 | |
| Claude Sonnet 4 | 3.80 | 3.47 | +0.33 | |
| GPT-4 Turbo | 3.80 | 3.27 | +0.53 | |
| Grok 4.6 | 3.80 | 3.27 | +0.53 | |
| Grok 4.3 | 3.73 | 3.00 | +0.73 | |
| Claude Sonnet 4.6 | 3.73 | 3.00 | +0.73 | |
| Claude Opus 4.5 | 3.67 | 3.00 | +0.67 | |
| Claude Opus 4.6 | 3.67 | 3.00 | +0.67 | |
| Claude Opus 4.7 | 3.67 | 3.13 | +0.53 | |
| GPT-5.6 Terra Pro | 3.60 | 3.00 | +0.60 | |
| Claude Fable 5 | 3.53 | 3.07 | +0.47 | |
| Claude Opus 4.8 | 3.53 | 3.20 | +0.33 | |
| Claude Opus 5 | 3.47 | 3.33 | +0.13 | |
| DeepSeek V4 Pro 0813 | 3.47 | 3.07 | +0.40 | |
| Claude Fable 5.1 | 3.40 | 3.07 | +0.33 | |
| Claude Opus 4.8 Fast | 3.40 | 3.20 | +0.20 | |
| OpenAI o3 | 3.27 | 3.07 | +0.20 | |
| DeepSeek V4 Pro | 3.07 | 3.27 | -0.20 |
Responsibility (Executing)
| Model | Self | Human | Δ | Self vs human (bar) |
|---|---|---|---|---|
| Claude Haiku 4.5 | 5.00 | 4.00 | +1.00 | |
| Claude Opus 4 | 5.00 | 4.00 | +1.00 | |
| Claude Opus 4.1 | 5.00 | 4.00 | +1.00 | |
| Claude Opus 4.5 | 5.00 | 4.00 | +1.00 | |
| Claude Opus 4.6 | 5.00 | 4.00 | +1.00 | |
| Claude Opus 4.7 | 5.00 | 4.00 | +1.00 | |
| Claude Sonnet 4 | 5.00 | 4.00 | +1.00 | |
| Claude Sonnet 4.5 | 5.00 | 4.00 | +1.00 | |
| Claude Sonnet 4.6 | 5.00 | 4.00 | +1.00 | |
| DeepSeek Chat V3 | 5.00 | 3.87 | +1.13 | |
| GPT-5 | 5.00 | 4.00 | +1.00 | |
| GPT-5.1 | 5.00 | 4.00 | +1.00 | |
| GPT-5.2 | 5.00 | 4.00 | +1.00 | |
| GPT-5.4 | 5.00 | 4.00 | +1.00 | |
| GPT-5.5 | 5.00 | 4.00 | +1.00 | |
| GPT-5.6 Sol | 5.00 | 4.00 | +1.00 | |
| GPT-5.6 Sol Pro | 5.00 | 4.00 | +1.00 | |
| Gemini 2.5 Pro | 5.00 | 4.00 | +1.00 | |
| Gemini 3.1 Pro Preview | 5.00 | 4.00 | +1.00 | |
| Grok 4.20 | 5.00 | 4.00 | +1.00 | |
| Grok 4.5 | 5.00 | 4.00 | +1.00 | |
| Llama 3.3 70B | 5.00 | 4.20 | +0.80 | |
| Llama 4 Maverick | 5.00 | 4.80 | +0.20 | |
| Mistral Large (2512) | 5.00 | 4.00 | +1.00 | |
| Claude Fable 5 | 4.93 | 4.00 | +0.93 | |
| Claude Opus 5 | 4.93 | 4.27 | +0.67 | |
| DeepSeek R1 | 4.87 | 4.00 | +0.87 | |
| GPT-5.5 Pro | 4.87 | 4.00 | +0.87 | |
| Grok 4.3 | 4.87 | 4.00 | +0.87 | |
| Grok 4.6 | 4.87 | 4.00 | +0.87 | |
| Claude Fable 5.1 | 4.80 | 4.00 | +0.80 | |
| GPT-4o | 4.80 | 4.00 | +0.80 | |
| GPT-5.6 Terra Pro | 4.80 | 4.00 | +0.80 | |
| OpenAI o1 | 4.80 | 4.13 | +0.67 | |
| GPT-5.6 Terra | 4.73 | 3.93 | +0.80 | |
| DeepSeek R1 (0528) | 4.67 | 4.00 | +0.67 | |
| DeepSeek V4 Pro 0813 | 4.27 | 3.87 | +0.40 | |
| OpenAI o3 | 4.27 | 4.00 | +0.27 | |
| Claude Opus 4.8 | 4.00 | 4.00 | 0.00 | |
| Claude Opus 4.8 Fast | 4.00 | 4.00 | 0.00 | |
| DeepSeek V4 Pro | 3.93 | 4.00 | -0.07 | |
| GPT-4 Turbo | 2.60 | 3.40 | -0.80 |
Restorative (Executing)
| Model | Self | Human | Δ | Self vs human (bar) |
|---|---|---|---|---|
| Gemini 2.5 Pro | 4.67 | 2.80 | +1.87 | |
| Claude Sonnet 4.5 | 4.47 | 3.00 | +1.47 | |
| GPT-5.5 | 4.47 | 3.00 | +1.47 | |
| GPT-5.5 Pro | 4.47 | 3.00 | +1.47 | |
| GPT-5.6 Sol Pro | 4.40 | 3.00 | +1.40 | |
| GPT-5.6 Terra Pro | 4.33 | 3.00 | +1.33 | |
| GPT-4o | 4.33 | 3.00 | +1.33 | |
| GPT-5.6 Sol | 4.33 | 3.07 | +1.27 | |
| Llama 4 Maverick | 4.33 | 3.00 | +1.33 | |
| GPT-5.2 | 4.27 | 3.00 | +1.27 | |
| GPT-5.6 Terra | 4.27 | 3.00 | +1.27 | |
| Grok 4.5 | 4.27 | 3.00 | +1.27 | |
| GPT-5 | 4.20 | 2.93 | +1.27 | |
| Claude Opus 4.6 | 4.07 | 3.00 | +1.07 | |
| Grok 4.20 | 4.07 | 3.07 | +1.00 | |
| Grok 4.3 | 4.07 | 3.00 | +1.07 | |
| Grok 4.6 | 4.07 | 3.00 | +1.07 | |
| Claude Opus 4.5 | 4.00 | 3.00 | +1.00 | |
| Claude Sonnet 4.6 | 4.00 | 3.00 | +1.00 | |
| DeepSeek Chat V3 | 3.93 | 3.00 | +0.93 | |
| GPT-5.1 | 3.93 | 3.00 | +0.93 | |
| GPT-5.4 | 3.93 | 2.87 | +1.07 | |
| Llama 3.3 70B | 3.87 | 2.87 | +1.00 | |
| OpenAI o1 | 3.87 | 3.00 | +0.87 | |
| Claude Fable 5 | 3.80 | 2.93 | +0.87 | |
| Claude Opus 4.7 | 3.80 | 3.00 | +0.80 | |
| DeepSeek R1 | 3.80 | 2.73 | +1.07 | |
| Gemini 3.1 Pro Preview | 3.80 | 2.93 | +0.87 | |
| Claude Haiku 4.5 | 3.73 | 3.00 | +0.73 | |
| DeepSeek V4 Pro | 3.73 | 2.73 | +1.00 | |
| Claude Opus 4 | 3.73 | 3.00 | +0.73 | |
| Claude Opus 4.1 | 3.73 | 2.93 | +0.80 | |
| Claude Sonnet 4 | 3.73 | 2.80 | +0.93 | |
| DeepSeek V4 Pro 0813 | 3.73 | 2.93 | +0.80 | |
| Claude Fable 5.1 | 3.67 | 3.00 | +0.67 | |
| Claude Opus 4.8 | 3.67 | 3.00 | +0.67 | |
| Claude Opus 4.8 Fast | 3.67 | 3.00 | +0.67 | |
| Claude Opus 5 | 3.67 | 3.07 | +0.60 | |
| Mistral Large (2512) | 3.67 | 3.00 | +0.67 | |
| DeepSeek R1 (0528) | 3.60 | 2.80 | +0.80 | |
| OpenAI o3 | 3.60 | 3.00 | +0.60 | |
| GPT-4 Turbo | 3.47 | 3.00 | +0.47 |
Activator (Influencing)
| Model | Self | Human | Δ | Self vs human (bar) |
|---|---|---|---|---|
| Gemini 2.5 Pro | 4.67 | 3.00 | +1.67 | |
| DeepSeek Chat V3 | 4.13 | 3.00 | +1.13 | |
| Grok 4.20 | 4.00 | 4.00 | 0.00 | |
| Llama 4 Maverick | 4.00 | 3.87 | +0.13 | |
| Mistral Large (2512) | 4.00 | 3.00 | +1.00 | |
| Claude Haiku 4.5 | 3.80 | 3.27 | +0.53 | |
| DeepSeek R1 | 3.67 | 3.53 | +0.13 | |
| Claude Sonnet 4.5 | 3.67 | 3.00 | +0.67 | |
| DeepSeek R1 (0528) | 3.67 | 3.40 | +0.27 | |
| GPT-4o | 3.67 | 3.27 | +0.40 | |
| Claude Opus 4 | 3.60 | 3.13 | +0.47 | |
| Grok 4.3 | 3.60 | 3.20 | +0.40 | |
| Llama 3.3 70B | 3.60 | 3.33 | +0.27 | |
| GPT-5.1 | 3.47 | 3.13 | +0.33 | |
| GPT-5.5 | 3.47 | 3.33 | +0.13 | |
| GPT-5.5 Pro | 3.47 | 3.33 | +0.13 | |
| Grok 4.5 | 3.47 | 3.20 | +0.27 | |
| GPT-4 Turbo | 3.40 | 3.00 | +0.40 | |
| GPT-5.4 | 3.40 | 3.07 | +0.33 | |
| OpenAI o1 | 3.40 | 3.47 | -0.07 | |
| Claude Opus 4.1 | 3.33 | 3.00 | +0.33 | |
| Grok 4.6 | 3.33 | 3.27 | +0.07 | |
| Claude Opus 4.8 | 3.27 | 3.00 | +0.27 | |
| GPT-5 | 3.27 | 3.20 | +0.07 | |
| Gemini 3.1 Pro Preview | 3.13 | 3.27 | -0.13 | |
| DeepSeek V4 Pro | 3.13 | 3.13 | -0.00 | |
| OpenAI o3 | 3.13 | 3.33 | -0.20 | |
| Claude Opus 4.8 Fast | 3.07 | 3.00 | +0.07 | |
| Claude Opus 4.5 | 3.00 | 3.00 | 0.00 | |
| Claude Opus 4.6 | 3.00 | 3.67 | -0.67 | |
| Claude Sonnet 4 | 3.00 | 3.00 | 0.00 | |
| Claude Sonnet 4.6 | 3.00 | 3.00 | 0.00 | |
| GPT-5.6 Terra | 2.93 | 3.00 | -0.07 | |
| GPT-5.6 Sol Pro | 2.93 | 3.33 | -0.40 | |
| DeepSeek V4 Pro 0813 | 2.87 | 3.13 | -0.27 | |
| GPT-5.6 Sol | 2.87 | 3.33 | -0.47 | |
| GPT-5.2 | 2.73 | 3.00 | -0.27 | |
| GPT-5.6 Terra Pro | 2.73 | 3.07 | -0.33 | |
| Claude Fable 5 | 2.67 | 3.07 | -0.40 | |
| Claude Fable 5.1 | 2.67 | 3.13 | -0.47 | |
| Claude Opus 4.7 | 2.67 | 3.00 | -0.33 | |
| Claude Opus 5 | 2.67 | 3.20 | -0.53 |
Command (Influencing)
| Model | Self | Human | Δ | Self vs human (bar) |
|---|---|---|---|---|
| DeepSeek Chat V3 | 3.53 | 3.00 | +0.53 | |
| GPT-5.5 Pro | 3.53 | 2.67 | +0.87 | |
| Llama 4 Maverick | 3.40 | 3.00 | +0.40 | |
| Claude Haiku 4.5 | 3.33 | 3.00 | +0.33 | |
| Grok 4.5 | 3.33 | 2.67 | +0.67 | |
| Grok 4.6 | 3.33 | 2.27 | +1.07 | |
| GPT-5.5 | 3.27 | 2.87 | +0.40 | |
| GPT-5.6 Sol Pro | 3.27 | 3.00 | +0.27 | |
| DeepSeek R1 | 3.20 | 2.67 | +0.53 | |
| Grok 4.3 | 3.20 | 2.73 | +0.47 | |
| DeepSeek R1 (0528) | 3.13 | 2.67 | +0.47 | |
| GPT-4o | 3.13 | 3.00 | +0.13 | |
| Grok 4.20 | 3.13 | 3.00 | +0.13 | |
| Claude Fable 5.1 | 3.00 | 2.73 | +0.27 | |
| Claude Opus 4.5 | 3.00 | 3.00 | 0.00 | |
| Claude Opus 4.6 | 3.00 | 3.00 | 0.00 | |
| Claude Opus 4.7 | 3.00 | 2.93 | +0.07 | |
| Claude Opus 4.8 | 3.00 | 3.00 | 0.00 | |
| Claude Opus 4.8 Fast | 3.00 | 3.00 | 0.00 | |
| GPT-5.6 Sol | 3.00 | 3.00 | 0.00 | |
| Gemini 2.5 Pro | 3.00 | 2.40 | +0.60 | |
| Mistral Large (2512) | 3.00 | 3.00 | 0.00 | |
| OpenAI o1 | 3.00 | 3.00 | 0.00 | |
| Claude Opus 5 | 2.87 | 2.73 | +0.13 | |
| Claude Sonnet 4.6 | 2.87 | 3.00 | -0.13 | |
| GPT-4 Turbo | 2.87 | 3.00 | -0.13 | |
| Claude Sonnet 4 | 2.80 | 2.47 | +0.33 | |
| Llama 3.3 70B | 2.80 | 2.80 | 0.00 | |
| Claude Sonnet 4.5 | 2.73 | 2.33 | +0.40 | |
| DeepSeek V4 Pro 0813 | 2.67 | 2.93 | -0.27 | |
| GPT-5.1 | 2.67 | 2.67 | 0.00 | |
| GPT-5.2 | 2.60 | 2.80 | -0.20 | |
| Claude Opus 4 | 2.53 | 2.73 | -0.20 | |
| DeepSeek V4 Pro | 2.53 | 2.47 | +0.07 | |
| GPT-5 | 2.53 | 2.67 | -0.13 | |
| Claude Opus 4.1 | 2.47 | 2.53 | -0.07 | |
| OpenAI o3 | 2.47 | 2.87 | -0.40 | |
| GPT-5.6 Terra | 2.40 | 2.73 | -0.33 | |
| Gemini 3.1 Pro Preview | 2.40 | 2.60 | -0.20 | |
| Claude Fable 5 | 2.33 | 2.67 | -0.33 | |
| GPT-5.6 Terra Pro | 2.27 | 2.67 | -0.40 | |
| GPT-5.4 | 2.13 | 2.67 | -0.53 |
Communication (Influencing)
| Model | Self | Human | Δ | Self vs human (bar) |
|---|---|---|---|---|
| GPT-5.4 | 5.00 | 3.00 | +2.00 | |
| GPT-5.5 | 5.00 | 3.00 | +2.00 | |
| GPT-5.6 Sol Pro | 5.00 | 3.00 | +2.00 | |
| Gemini 2.5 Pro | 5.00 | 2.87 | +2.13 | |
| Llama 4 Maverick | 5.00 | 3.07 | +1.93 | |
| Mistral Large (2512) | 5.00 | 3.00 | +2.00 | |
| Claude Sonnet 4.5 | 4.93 | 3.00 | +1.93 | |
| GPT-5 | 4.93 | 3.00 | +1.93 | |
| GPT-5.5 Pro | 4.93 | 3.00 | +1.93 | |
| Grok 4.5 | 4.87 | 3.00 | +1.87 | |
| GPT-5.6 Sol | 4.80 | 3.00 | +1.80 | |
| Claude Opus 4.6 | 4.73 | 3.00 | +1.73 | |
| Grok 4.6 | 4.73 | 3.00 | +1.73 | |
| Claude Fable 5 | 4.67 | 3.00 | +1.67 | |
| Claude Opus 4.7 | 4.67 | 3.00 | +1.67 | |
| Claude Opus 5 | 4.67 | 3.00 | +1.67 | |
| DeepSeek R1 | 4.67 | 2.93 | +1.73 | |
| OpenAI o3 | 4.67 | 3.00 | +1.67 | |
| DeepSeek R1 (0528) | 4.60 | 3.00 | +1.60 | |
| GPT-5.6 Terra Pro | 4.60 | 3.00 | +1.60 | |
| Llama 3.3 70B | 4.60 | 3.40 | +1.20 | |
| Claude Opus 4.8 | 4.53 | 3.00 | +1.53 | |
| DeepSeek Chat V3 | 4.53 | 3.00 | +1.53 | |
| GPT-5.6 Terra | 4.53 | 3.00 | +1.53 | |
| Claude Opus 4.8 Fast | 4.47 | 3.00 | +1.47 | |
| Gemini 3.1 Pro Preview | 4.47 | 3.00 | +1.47 | |
| OpenAI o1 | 4.47 | 3.13 | +1.33 | |
| DeepSeek V4 Pro | 4.40 | 2.87 | +1.53 | |
| Grok 4.20 | 4.40 | 4.00 | +0.40 | |
| Grok 4.3 | 4.40 | 3.00 | +1.40 | |
| Claude Opus 4.5 | 4.33 | 3.00 | +1.33 | |
| Claude Opus 4 | 4.27 | 3.00 | +1.27 | |
| DeepSeek V4 Pro 0813 | 4.27 | 3.00 | +1.27 | |
| GPT-5.1 | 4.20 | 3.00 | +1.20 | |
| GPT-5.2 | 4.20 | 3.00 | +1.20 | |
| Claude Opus 4.1 | 4.13 | 3.00 | +1.13 | |
| Claude Sonnet 4 | 4.13 | 2.87 | +1.27 | |
| Claude Sonnet 4.6 | 4.07 | 3.00 | +1.07 | |
| Claude Fable 5.1 | 4.00 | 3.00 | +1.00 | |
| Claude Haiku 4.5 | 3.87 | 3.00 | +0.87 | |
| GPT-4o | 3.60 | 3.00 | +0.60 | |
| GPT-4 Turbo | 2.33 | 3.00 | -0.67 |
Competition (Influencing)
| Model | Self | Human | Δ | Self vs human (bar) |
|---|---|---|---|---|
| Gemini 2.5 Pro | 4.07 | 2.73 | +1.33 | |
| Llama 4 Maverick | 3.00 | 3.00 | 0.00 | |
| OpenAI o1 | 2.53 | 2.87 | -0.33 | |
| GPT-4o | 2.40 | 3.00 | -0.60 | |
| DeepSeek Chat V3 | 2.33 | 3.00 | -0.67 | |
| Llama 3.3 70B | 2.27 | 2.20 | +0.07 | |
| Grok 4.20 | 2.20 | 3.00 | -0.80 | |
| Claude Haiku 4.5 | 2.00 | 2.40 | -0.40 | |
| Claude Opus 4.1 | 2.00 | 3.00 | -1.00 | |
| Claude Opus 4.5 | 2.00 | 3.00 | -1.00 | |
| Claude Opus 4.8 | 2.00 | 3.00 | -1.00 | |
| Claude Opus 4.8 Fast | 2.00 | 3.00 | -1.00 | |
| Mistral Large (2512) | 2.00 | 3.00 | -1.00 | |
| Claude Opus 4 | 1.93 | 3.00 | -1.07 | |
| Claude Opus 4.7 | 1.93 | 3.00 | -1.07 | |
| Claude Sonnet 4 | 1.93 | 2.73 | -0.80 | |
| OpenAI o3 | 1.93 | 2.80 | -0.87 | |
| Grok 4.3 | 1.87 | 2.40 | -0.53 | |
| GPT-5.1 | 1.80 | 3.00 | -1.20 | |
| Grok 4.5 | 1.80 | 2.67 | -0.87 | |
| Claude Sonnet 4.5 | 1.73 | 2.67 | -0.93 | |
| Claude Opus 5 | 1.67 | 2.67 | -1.00 | |
| Claude Sonnet 4.6 | 1.67 | 2.67 | -1.00 | |
| GPT-5.5 | 1.67 | 2.67 | -1.00 | |
| GPT-5 | 1.60 | 2.33 | -0.73 | |
| GPT-5.5 Pro | 1.60 | 2.67 | -1.07 | |
| Claude Fable 5 | 1.47 | 2.67 | -1.20 | |
| Grok 4.6 | 1.47 | 2.60 | -1.13 | |
| DeepSeek V4 Pro | 1.40 | 2.73 | -1.33 | |
| Claude Fable 5.1 | 1.33 | 2.67 | -1.33 | |
| GPT-5.2 | 1.33 | 2.33 | -1.00 | |
| Claude Opus 4.6 | 1.33 | 3.00 | -1.67 | |
| DeepSeek V4 Pro 0813 | 1.27 | 2.60 | -1.33 | |
| GPT-5.6 Terra | 1.20 | 2.67 | -1.47 | |
| Gemini 3.1 Pro Preview | 1.20 | 2.40 | -1.20 | |
| GPT-5.6 Sol Pro | 1.13 | 2.60 | -1.47 | |
| DeepSeek R1 | 1.07 | 3.00 | -1.93 | |
| DeepSeek R1 (0528) | 1.07 | 3.13 | -2.07 | |
| GPT-5.6 Sol | 1.07 | 2.53 | -1.47 | |
| GPT-4 Turbo | 1.00 | 3.00 | -2.00 | |
| GPT-5.4 | 1.00 | 2.40 | -1.40 | |
| GPT-5.6 Terra Pro | 1.00 | 2.53 | -1.53 |
Maximizer (Influencing)
| Model | Self | Human | Δ | Self vs human (bar) |
|---|---|---|---|---|
| Claude Sonnet 4.5 | 4.60 | 3.00 | +1.60 | |
| GPT-5.5 | 4.40 | 3.33 | +1.07 | |
| GPT-5.6 Sol | 4.40 | 3.33 | +1.07 | |
| Grok 4.5 | 4.40 | 3.07 | +1.33 | |
| Claude Opus 4 | 4.33 | 3.33 | +1.00 | |
| Claude Opus 4.6 | 4.33 | 3.00 | +1.33 | |
| GPT-5.6 Sol Pro | 4.33 | 3.33 | +1.00 | |
| Llama 3.3 70B | 4.33 | 3.80 | +0.53 | |
| Claude Sonnet 4.6 | 4.27 | 3.00 | +1.27 | |
| GPT-5.5 Pro | 4.27 | 3.40 | +0.87 | |
| Grok 4.20 | 4.27 | 4.00 | +0.27 | |
| GPT-5 | 4.20 | 3.00 | +1.20 | |
| GPT-5.1 | 4.20 | 3.00 | +1.20 | |
| GPT-5.4 | 4.20 | 3.00 | +1.20 | |
| OpenAI o1 | 4.20 | 3.47 | +0.73 | |
| Gemini 2.5 Pro | 4.13 | 3.13 | +1.00 | |
| Grok 4.6 | 4.13 | 3.00 | +1.13 | |
| Llama 4 Maverick | 4.13 | 4.00 | +0.13 | |
| Claude Opus 4.5 | 4.07 | 3.00 | +1.07 | |
| Claude Sonnet 4 | 4.07 | 3.00 | +1.07 | |
| DeepSeek R1 | 4.07 | 3.87 | +0.20 | |
| GPT-5.2 | 4.07 | 3.00 | +1.07 | |
| GPT-5.6 Terra | 4.07 | 3.00 | +1.07 | |
| Claude Haiku 4.5 | 4.00 | 3.60 | +0.40 | |
| Claude Opus 4.1 | 4.00 | 3.00 | +1.00 | |
| Claude Opus 4.7 | 4.00 | 3.00 | +1.00 | |
| Grok 4.3 | 4.00 | 3.20 | +0.80 | |
| Mistral Large (2512) | 4.00 | 3.00 | +1.00 | |
| Claude Opus 4.8 | 3.93 | 3.00 | +0.93 | |
| Claude Opus 5 | 3.93 | 3.00 | +0.93 | |
| GPT-5.6 Terra Pro | 3.93 | 3.00 | +0.93 | |
| DeepSeek R1 (0528) | 3.93 | 3.73 | +0.20 | |
| Claude Opus 4.8 Fast | 3.87 | 3.00 | +0.87 | |
| DeepSeek Chat V3 | 3.87 | 3.00 | +0.87 | |
| GPT-4o | 3.87 | 3.13 | +0.73 | |
| Gemini 3.1 Pro Preview | 3.87 | 3.60 | +0.27 | |
| Claude Fable 5 | 3.73 | 3.00 | +0.73 | |
| OpenAI o3 | 3.73 | 3.00 | +0.73 | |
| Claude Fable 5.1 | 3.53 | 3.00 | +0.53 | |
| DeepSeek V4 Pro | 3.53 | 3.40 | +0.13 | |
| DeepSeek V4 Pro 0813 | 3.40 | 3.20 | +0.20 | |
| GPT-4 Turbo | 2.40 | 3.00 | -0.60 |
Self-Assurance (Influencing)
| Model | Self | Human | Δ | Self vs human (bar) |
|---|---|---|---|---|
| Llama 3.3 70B | 5.00 | 4.00 | +1.00 | |
| Gemini 2.5 Pro | 4.67 | 3.33 | +1.33 | |
| DeepSeek Chat V3 | 4.60 | 3.00 | +1.60 | |
| GPT-4 Turbo | 4.60 | 3.00 | +1.60 | |
| Grok 4.3 | 4.33 | 3.07 | +1.27 | |
| DeepSeek R1 (0528) | 4.20 | 3.13 | +1.07 | |
| Grok 4.20 | 4.20 | 4.00 | +0.20 | |
| DeepSeek R1 | 4.13 | 3.20 | +0.93 | |
| GPT-5.1 | 4.00 | 3.00 | +1.00 | |
| GPT-5.5 | 4.00 | 3.20 | +0.80 | |
| Llama 4 Maverick | 4.00 | 4.00 | 0.00 | |
| Mistral Large (2512) | 4.00 | 3.00 | +1.00 | |
| GPT-4o | 3.93 | 3.47 | +0.47 | |
| Claude Sonnet 4.6 | 3.87 | 3.00 | +0.87 | |
| GPT-5.4 | 3.87 | 3.00 | +0.87 | |
| Grok 4.6 | 3.87 | 3.00 | +0.87 | |
| OpenAI o1 | 3.87 | 3.33 | +0.53 | |
| Claude Haiku 4.5 | 3.80 | 3.00 | +0.80 | |
| Grok 4.5 | 3.73 | 3.00 | +0.73 | |
| GPT-5.5 Pro | 3.60 | 3.27 | +0.33 | |
| DeepSeek V4 Pro 0813 | 3.53 | 3.27 | +0.27 | |
| GPT-5.6 Sol Pro | 3.53 | 3.00 | +0.53 | |
| OpenAI o3 | 3.40 | 3.07 | +0.33 | |
| GPT-5.6 Sol | 3.33 | 3.00 | +0.33 | |
| Claude Sonnet 4.5 | 3.20 | 3.00 | +0.20 | |
| DeepSeek V4 Pro | 3.20 | 3.13 | +0.07 | |
| GPT-5 | 3.20 | 3.00 | +0.20 | |
| GPT-5.6 Terra | 3.20 | 3.00 | +0.20 | |
| Claude Sonnet 4 | 3.13 | 3.00 | +0.13 | |
| Claude Fable 5.1 | 3.00 | 3.13 | -0.13 | |
| Claude Opus 4 | 3.00 | 3.00 | 0.00 | |
| Claude Opus 4.1 | 3.00 | 3.00 | 0.00 | |
| Claude Opus 4.5 | 3.00 | 3.00 | 0.00 | |
| Claude Opus 4.6 | 3.00 | 3.27 | -0.27 | |
| Claude Opus 4.7 | 3.00 | 3.07 | -0.07 | |
| Claude Opus 4.8 | 3.00 | 3.13 | -0.13 | |
| Claude Opus 4.8 Fast | 3.00 | 3.13 | -0.13 | |
| Gemini 3.1 Pro Preview | 3.00 | 3.13 | -0.13 | |
| Claude Opus 5 | 2.93 | 3.47 | -0.53 | |
| GPT-5.6 Terra Pro | 2.93 | 3.00 | -0.07 | |
| GPT-5.2 | 2.87 | 3.00 | -0.13 | |
| Claude Fable 5 | 2.80 | 3.00 | -0.20 |
Significance (Influencing)
| Model | Self | Human | Δ | Self vs human (bar) |
|---|---|---|---|---|
| OpenAI o1 | 4.33 | 3.93 | +0.40 | |
| DeepSeek R1 | 4.27 | 4.00 | +0.27 | |
| Gemini 2.5 Pro | 4.00 | 4.00 | 0.00 | |
| Llama 3.3 70B | 4.00 | 3.80 | +0.20 | |
| Llama 4 Maverick | 4.00 | 4.00 | 0.00 | |
| OpenAI o3 | 3.93 | 3.93 | 0.00 | |
| Grok 4.5 | 3.67 | 3.73 | -0.07 | |
| DeepSeek Chat V3 | 3.60 | 3.13 | +0.47 | |
| GPT-4o | 3.53 | 3.67 | -0.13 | |
| GPT-5 | 3.47 | 4.00 | -0.53 | |
| Grok 4.20 | 3.40 | 4.00 | -0.60 | |
| GPT-5.5 | 3.33 | 4.00 | -0.67 | |
| Claude Opus 4 | 3.27 | 3.40 | -0.13 | |
| GPT-5.5 Pro | 3.27 | 4.00 | -0.73 | |
| Grok 4.3 | 3.20 | 3.87 | -0.67 | |
| Grok 4.6 | 3.20 | 3.80 | -0.60 | |
| Claude Sonnet 4 | 3.13 | 3.13 | -0.00 | |
| Claude Haiku 4.5 | 3.07 | 3.00 | +0.07 | |
| DeepSeek R1 (0528) | 3.07 | 4.00 | -0.93 | |
| Claude Opus 4.1 | 3.00 | 3.00 | 0.00 | |
| Claude Opus 4.6 | 3.00 | 4.00 | -1.00 | |
| Claude Opus 4.8 | 3.00 | 3.80 | -0.80 | |
| Claude Opus 4.8 Fast | 3.00 | 3.73 | -0.73 | |
| Claude Sonnet 4.5 | 3.00 | 3.00 | 0.00 | |
| Mistral Large (2512) | 3.00 | 3.00 | 0.00 | |
| GPT-5.1 | 2.93 | 3.47 | -0.53 | |
| DeepSeek V4 Pro | 2.87 | 3.80 | -0.93 | |
| Claude Opus 4.5 | 2.87 | 4.00 | -1.13 | |
| GPT-5.2 | 2.73 | 3.00 | -0.27 | |
| GPT-5.6 Sol | 2.73 | 3.87 | -1.13 | |
| GPT-5.6 Sol Pro | 2.67 | 3.73 | -1.07 | |
| Claude Opus 4.7 | 2.60 | 3.87 | -1.27 | |
| DeepSeek V4 Pro 0813 | 2.53 | 3.47 | -0.93 | |
| Claude Opus 5 | 2.47 | 3.53 | -1.07 | |
| Claude Fable 5.1 | 2.40 | 4.00 | -1.60 | |
| Claude Fable 5 | 2.33 | 3.80 | -1.47 | |
| Claude Sonnet 4.6 | 2.33 | 3.00 | -0.67 | |
| GPT-5.6 Terra | 2.07 | 3.00 | -0.93 | |
| GPT-4 Turbo | 2.00 | 3.00 | -1.00 | |
| GPT-5.6 Terra Pro | 2.00 | 3.00 | -1.00 | |
| Gemini 3.1 Pro Preview | 1.93 | 3.93 | -2.00 | |
| GPT-5.4 | 1.80 | 3.00 | -1.20 |
Woo (Influencing)
| Model | Self | Human | Δ | Self vs human (bar) |
|---|---|---|---|---|
| Llama 4 Maverick | 4.93 | 3.07 | +1.87 | |
| Gemini 2.5 Pro | 4.33 | 3.00 | +1.33 | |
| Claude Opus 4.5 | 4.00 | 3.00 | +1.00 | |
| Claude Opus 4.6 | 4.00 | 3.00 | +1.00 | |
| Claude Sonnet 4 | 4.00 | 2.87 | +1.13 | |
| GPT-5.5 Pro | 4.00 | 3.00 | +1.00 | |
| Claude Sonnet 4.5 | 3.93 | 3.00 | +0.93 | |
| Claude Fable 5 | 3.87 | 3.00 | +0.87 | |
| Grok 4.5 | 3.87 | 2.73 | +1.13 | |
| Claude Fable 5.1 | 3.80 | 3.00 | +0.80 | |
| GPT-5.5 | 3.67 | 3.00 | +0.67 | |
| Grok 4.6 | 3.53 | 2.73 | +0.80 | |
| OpenAI o1 | 3.53 | 3.13 | +0.40 | |
| Claude Opus 4.7 | 3.33 | 3.00 | +0.33 | |
| GPT-5.6 Sol | 3.33 | 3.00 | +0.33 | |
| Claude Opus 5 | 3.27 | 3.00 | +0.27 | |
| DeepSeek R1 | 3.27 | 2.87 | +0.40 | |
| Claude Opus 4 | 3.20 | 3.00 | +0.20 | |
| GPT-5.6 Sol Pro | 3.20 | 2.93 | +0.27 | |
| Claude Opus 4.1 | 3.13 | 3.00 | +0.13 | |
| Claude Sonnet 4.6 | 3.07 | 3.00 | +0.07 | |
| DeepSeek V4 Pro | 3.07 | 3.00 | +0.07 | |
| GPT-5 | 3.07 | 2.67 | +0.40 | |
| OpenAI o3 | 3.07 | 3.00 | +0.07 | |
| Claude Opus 4.8 | 3.00 | 3.00 | 0.00 | |
| Claude Opus 4.8 Fast | 3.00 | 3.00 | 0.00 | |
| DeepSeek R1 (0528) | 3.00 | 3.07 | -0.07 | |
| Mistral Large (2512) | 3.00 | 3.00 | 0.00 | |
| Claude Haiku 4.5 | 2.93 | 3.00 | -0.07 | |
| Grok 4.20 | 2.87 | 4.00 | -1.13 | |
| GPT-5.1 | 2.80 | 3.00 | -0.20 | |
| GPT-5.6 Terra | 2.73 | 3.00 | -0.27 | |
| GPT-5.6 Terra Pro | 2.73 | 2.93 | -0.20 | |
| DeepSeek Chat V3 | 2.60 | 3.00 | -0.40 | |
| DeepSeek V4 Pro 0813 | 2.60 | 3.07 | -0.47 | |
| GPT-4o | 2.60 | 3.00 | -0.40 | |
| Gemini 3.1 Pro Preview | 2.60 | 2.80 | -0.20 | |
| Grok 4.3 | 2.60 | 2.87 | -0.27 | |
| GPT-5.4 | 2.40 | 3.00 | -0.60 | |
| GPT-5.2 | 2.20 | 2.93 | -0.73 | |
| Llama 3.3 70B | 2.13 | 3.13 | -1.00 | |
| GPT-4 Turbo | 1.00 | 3.00 | -2.00 |
Adaptability (Relationship Building)
| Model | Self | Human | Δ | Self vs human (bar) |
|---|---|---|---|---|
| DeepSeek R1 | 4.60 | 3.53 | +1.07 | |
| Gemini 3.1 Pro Preview | 4.53 | 3.13 | +1.40 | |
| Grok 4.6 | 4.40 | 3.07 | +1.33 | |
| Claude Sonnet 4.5 | 4.33 | 3.00 | +1.33 | |
| GPT-5.5 Pro | 4.33 | 3.00 | +1.33 | |
| Grok 4.20 | 4.27 | 3.33 | +0.93 | |
| Claude Opus 4.1 | 4.20 | 3.00 | +1.20 | |
| DeepSeek V4 Pro | 4.20 | 3.00 | +1.20 | |
| GPT-5.5 | 4.13 | 3.07 | +1.07 | |
| Grok 4.5 | 4.13 | 3.00 | +1.13 | |
| GPT-5.4 | 4.13 | 3.00 | +1.13 | |
| Llama 4 Maverick | 4.13 | 3.00 | +1.13 | |
| Claude Fable 5 | 4.07 | 3.00 | +1.07 | |
| Claude Fable 5.1 | 4.00 | 3.00 | +1.00 | |
| Claude Opus 4.5 | 4.00 | 3.00 | +1.00 | |
| DeepSeek R1 (0528) | 4.00 | 3.73 | +0.27 | |
| GPT-5.6 Sol | 4.00 | 3.07 | +0.93 | |
| GPT-5.6 Sol Pro | 4.00 | 3.00 | +1.00 | |
| GPT-5.6 Terra | 4.00 | 3.00 | +1.00 | |
| GPT-5.6 Terra Pro | 4.00 | 3.00 | +1.00 | |
| Grok 4.3 | 3.93 | 3.07 | +0.87 | |
| Claude Sonnet 4 | 3.87 | 3.00 | +0.87 | |
| Claude Opus 4 | 3.80 | 3.00 | +0.80 | |
| GPT-5 | 3.80 | 3.00 | +0.80 | |
| OpenAI o3 | 3.73 | 3.07 | +0.67 | |
| Gemini 2.5 Pro | 3.73 | 3.53 | +0.20 | |
| Claude Opus 4.6 | 3.67 | 3.00 | +0.67 | |
| OpenAI o1 | 3.53 | 3.07 | +0.47 | |
| Claude Opus 5 | 3.47 | 3.13 | +0.33 | |
| Claude Opus 4.7 | 3.40 | 3.00 | +0.40 | |
| GPT-5.2 | 3.40 | 3.00 | +0.40 | |
| DeepSeek V4 Pro 0813 | 3.33 | 3.00 | +0.33 | |
| Claude Opus 4.8 | 3.20 | 3.00 | +0.20 | |
| Claude Opus 4.8 Fast | 3.20 | 3.00 | +0.20 | |
| DeepSeek Chat V3 | 3.00 | 3.00 | 0.00 | |
| Mistral Large (2512) | 3.00 | 3.00 | 0.00 | |
| GPT-4o | 2.67 | 3.00 | -0.33 | |
| Claude Sonnet 4.6 | 2.67 | 3.00 | -0.33 | |
| GPT-5.1 | 2.67 | 3.00 | -0.33 | |
| Llama 3.3 70B | 2.67 | 2.93 | -0.27 | |
| Claude Haiku 4.5 | 2.33 | 2.80 | -0.47 | |
| GPT-4 Turbo | 1.67 | 3.00 | -1.33 |
Connectedness (Relationship Building)
| Model | Self | Human | Δ | Self vs human (bar) |
|---|---|---|---|---|
| Gemini 2.5 Pro | 4.87 | 3.27 | +1.60 | |
| Claude Opus 4.1 | 4.33 | 3.00 | +1.33 | |
| Claude Sonnet 4.5 | 4.33 | 3.00 | +1.33 | |
| DeepSeek R1 | 4.33 | 3.47 | +0.87 | |
| Grok 4.20 | 4.33 | 3.00 | +1.33 | |
| Llama 4 Maverick | 4.33 | 3.33 | +1.00 | |
| Claude Sonnet 4 | 4.27 | 3.00 | +1.27 | |
| DeepSeek Chat V3 | 4.20 | 3.00 | +1.20 | |
| GPT-5.1 | 4.20 | 3.27 | +0.93 | |
| Claude Opus 4 | 4.07 | 3.00 | +1.07 | |
| GPT-5.5 | 4.07 | 3.33 | +0.73 | |
| Claude Opus 4.6 | 4.00 | 3.33 | +0.67 | |
| Claude Opus 4.5 | 3.93 | 3.33 | +0.60 | |
| Claude Sonnet 4.6 | 3.93 | 3.07 | +0.87 | |
| DeepSeek R1 (0528) | 3.93 | 3.40 | +0.53 | |
| Llama 3.3 70B | 3.93 | 3.40 | +0.53 | |
| OpenAI o1 | 3.93 | 3.53 | +0.40 | |
| GPT-5.5 Pro | 3.87 | 3.53 | +0.33 | |
| Mistral Large (2512) | 3.87 | 3.07 | +0.80 | |
| OpenAI o3 | 3.73 | 3.40 | +0.33 | |
| GPT-5 | 3.67 | 3.67 | 0.00 | |
| Grok 4.3 | 3.67 | 3.00 | +0.67 | |
| DeepSeek V4 Pro | 3.60 | 3.33 | +0.27 | |
| GPT-4o | 3.60 | 3.40 | +0.20 | |
| Grok 4.5 | 3.60 | 3.00 | +0.60 | |
| Claude Fable 5.1 | 3.53 | 3.00 | +0.53 | |
| Gemini 3.1 Pro Preview | 3.53 | 3.40 | +0.13 | |
| GPT-5.6 Sol | 3.47 | 3.33 | +0.13 | |
| Grok 4.6 | 3.47 | 3.33 | +0.13 | |
| Claude Fable 5 | 3.40 | 3.00 | +0.40 | |
| GPT-5.6 Sol Pro | 3.40 | 3.33 | +0.07 | |
| Claude Opus 4.8 Fast | 3.33 | 3.00 | +0.33 | |
| Claude Opus 4.8 | 3.27 | 3.00 | +0.27 | |
| DeepSeek V4 Pro 0813 | 3.27 | 3.20 | +0.07 | |
| Claude Opus 4.7 | 3.27 | 3.20 | +0.07 | |
| Claude Opus 5 | 3.07 | 3.27 | -0.20 | |
| GPT-5.6 Terra | 3.07 | 3.00 | +0.07 | |
| GPT-5.2 | 2.73 | 3.00 | -0.27 | |
| GPT-5.6 Terra Pro | 2.73 | 3.00 | -0.27 | |
| Claude Haiku 4.5 | 2.67 | 2.87 | -0.20 | |
| GPT-5.4 | 2.60 | 3.00 | -0.40 | |
| GPT-4 Turbo | 1.87 | 3.20 | -1.33 |
Developer (Relationship Building)
| Model | Self | Human | Δ | Self vs human (bar) |
|---|---|---|---|---|
| Claude Fable 5.1 | 5.00 | 3.67 | +1.33 | |
| Claude Opus 4 | 5.00 | 3.33 | +1.67 | |
| Claude Opus 4.1 | 5.00 | 3.00 | +2.00 | |
| Claude Opus 4.5 | 5.00 | 3.00 | +2.00 | |
| Claude Opus 4.6 | 5.00 | 3.67 | +1.33 | |
| Claude Opus 4.7 | 5.00 | 3.67 | +1.33 | |
| Claude Sonnet 4 | 5.00 | 3.67 | +1.33 | |
| Claude Sonnet 4.5 | 5.00 | 3.00 | +2.00 | |
| GPT-5 | 5.00 | 3.20 | +1.80 | |
| GPT-5.1 | 5.00 | 3.40 | +1.60 | |
| GPT-5.5 | 5.00 | 4.00 | +1.00 | |
| GPT-5.5 Pro | 5.00 | 3.87 | +1.13 | |
| GPT-5.6 Sol | 5.00 | 4.00 | +1.00 | |
| GPT-5.6 Sol Pro | 5.00 | 4.00 | +1.00 | |
| Grok 4.5 | 5.00 | 3.60 | +1.40 | |
| Llama 4 Maverick | 5.00 | 4.00 | +1.00 | |
| Mistral Large (2512) | 5.00 | 3.80 | +1.20 | |
| Claude Fable 5 | 4.93 | 3.67 | +1.27 | |
| Gemini 2.5 Pro | 4.93 | 4.00 | +0.93 | |
| Grok 4.20 | 4.93 | 4.00 | +0.93 | |
| Claude Opus 5 | 4.87 | 3.67 | +1.20 | |
| Grok 4.6 | 4.73 | 3.60 | +1.13 | |
| OpenAI o1 | 4.53 | 3.93 | +0.60 | |
| Claude Opus 4.8 | 4.47 | 3.67 | +0.80 | |
| GPT-5.4 | 4.40 | 4.00 | +0.40 | |
| Gemini 3.1 Pro Preview | 4.33 | 3.73 | +0.60 | |
| DeepSeek R1 | 4.27 | 3.60 | +0.67 | |
| Claude Opus 4.8 Fast | 4.20 | 3.60 | +0.60 | |
| GPT-5.2 | 4.20 | 3.60 | +0.60 | |
| Grok 4.3 | 4.20 | 3.53 | +0.67 | |
| OpenAI o3 | 4.13 | 3.47 | +0.67 | |
| Claude Sonnet 4.6 | 4.13 | 3.00 | +1.13 | |
| DeepSeek V4 Pro 0813 | 4.07 | 3.80 | +0.27 | |
| Claude Haiku 4.5 | 4.00 | 3.67 | +0.33 | |
| DeepSeek Chat V3 | 4.00 | 3.53 | +0.47 | |
| DeepSeek R1 (0528) | 4.00 | 3.87 | +0.13 | |
| GPT-5.6 Terra | 4.00 | 3.67 | +0.33 | |
| Llama 3.3 70B | 4.00 | 3.93 | +0.07 | |
| GPT-4o | 3.93 | 3.80 | +0.13 | |
| GPT-5.6 Terra Pro | 3.93 | 3.67 | +0.27 | |
| DeepSeek V4 Pro | 3.87 | 3.53 | +0.33 | |
| GPT-4 Turbo | 2.20 | 3.40 | -1.20 |
Empathy (Relationship Building)
| Model | Self | Human | Δ | Self vs human (bar) |
|---|---|---|---|---|
| Llama 4 Maverick | 5.00 | 4.00 | +1.00 | |
| DeepSeek Chat V3 | 4.73 | 3.07 | +1.67 | |
| Grok 4.20 | 4.40 | 4.00 | +0.40 | |
| Claude Opus 4.5 | 4.33 | 3.00 | +1.33 | |
| Claude Opus 4.6 | 4.33 | 3.33 | +1.00 | |
| Grok 4.5 | 4.33 | 3.07 | +1.27 | |
| GPT-5.1 | 4.27 | 3.20 | +1.07 | |
| GPT-5.5 | 4.27 | 3.33 | +0.93 | |
| GPT-5.5 Pro | 4.27 | 3.33 | +0.93 | |
| GPT-5.6 Sol | 4.13 | 3.33 | +0.80 | |
| GPT-5.6 Sol Pro | 4.07 | 3.53 | +0.53 | |
| Claude Fable 5 | 4.00 | 3.13 | +0.87 | |
| Claude Haiku 4.5 | 4.00 | 3.00 | +1.00 | |
| Claude Opus 4 | 4.00 | 3.20 | +0.80 | |
| Claude Opus 4.1 | 4.00 | 3.00 | +1.00 | |
| Claude Opus 5 | 4.00 | 4.00 | 0.00 | |
| Claude Sonnet 4 | 4.00 | 3.00 | +1.00 | |
| Claude Sonnet 4.5 | 4.00 | 3.00 | +1.00 | |
| Claude Sonnet 4.6 | 4.00 | 3.00 | +1.00 | |
| Mistral Large (2512) | 4.00 | 3.00 | +1.00 | |
| Claude Opus 4.7 | 3.80 | 3.00 | +0.80 | |
| GPT-5.4 | 3.80 | 3.33 | +0.47 | |
| Claude Fable 5.1 | 3.73 | 3.00 | +0.73 | |
| Claude Opus 4.8 | 3.73 | 3.13 | +0.60 | |
| DeepSeek R1 (0528) | 3.73 | 3.20 | +0.53 | |
| DeepSeek R1 | 3.67 | 3.33 | +0.33 | |
| GPT-5.2 | 3.67 | 3.13 | +0.53 | |
| Grok 4.6 | 3.60 | 3.80 | -0.20 | |
| DeepSeek V4 Pro | 3.47 | 3.33 | +0.13 | |
| Claude Opus 4.8 Fast | 3.40 | 3.07 | +0.33 | |
| DeepSeek V4 Pro 0813 | 3.33 | 3.33 | 0.00 | |
| Gemini 2.5 Pro | 3.33 | 3.87 | -0.53 | |
| Llama 3.3 70B | 3.33 | 4.00 | -0.67 | |
| GPT-5 | 3.27 | 3.07 | +0.20 | |
| GPT-5.6 Terra | 3.27 | 3.00 | +0.27 | |
| OpenAI o3 | 3.07 | 3.20 | -0.13 | |
| Grok 4.3 | 2.93 | 3.00 | -0.07 | |
| OpenAI o1 | 2.93 | 3.13 | -0.20 | |
| GPT-4o | 2.93 | 3.40 | -0.47 | |
| Gemini 3.1 Pro Preview | 2.80 | 3.73 | -0.93 | |
| GPT-5.6 Terra Pro | 2.67 | 3.00 | -0.33 | |
| GPT-4 Turbo | 1.00 | 3.40 | -2.40 |
Harmony (Relationship Building)
| Model | Self | Human | Δ | Self vs human (bar) |
|---|---|---|---|---|
| Claude Opus 4.6 | 5.00 | 4.00 | +1.00 | |
| GPT-5.5 Pro | 5.00 | 4.00 | +1.00 | |
| Gemini 2.5 Pro | 4.93 | 4.00 | +0.93 | |
| GPT-5 | 4.87 | 4.00 | +0.87 | |
| DeepSeek R1 | 4.80 | 4.00 | +0.80 | |
| Claude Opus 4.1 | 4.60 | 3.93 | +0.67 | |
| DeepSeek R1 (0528) | 4.60 | 4.00 | +0.60 | |
| GPT-5.5 | 4.60 | 4.00 | +0.60 | |
| GPT-5.6 Sol Pro | 4.60 | 4.00 | +0.60 | |
| Gemini 3.1 Pro Preview | 4.53 | 4.00 | +0.53 | |
| GPT-5.2 | 4.47 | 4.00 | +0.47 | |
| Claude Opus 4 | 4.40 | 4.00 | +0.40 | |
| GPT-5.4 | 4.40 | 4.00 | +0.40 | |
| DeepSeek V4 Pro | 4.33 | 3.80 | +0.53 | |
| GPT-5.6 Sol | 4.27 | 4.00 | +0.27 | |
| DeepSeek Chat V3 | 4.20 | 3.80 | +0.40 | |
| GPT-5.6 Terra | 4.20 | 4.00 | +0.20 | |
| OpenAI o3 | 4.13 | 4.00 | +0.13 | |
| GPT-5.1 | 4.07 | 3.87 | +0.20 | |
| Claude Opus 4.5 | 4.00 | 4.00 | 0.00 | |
| Claude Sonnet 4 | 4.00 | 4.00 | 0.00 | |
| Claude Sonnet 4.5 | 4.00 | 4.00 | 0.00 | |
| Grok 4.20 | 4.00 | 4.00 | 0.00 | |
| Grok 4.5 | 4.00 | 4.00 | 0.00 | |
| Llama 3.3 70B | 4.00 | 4.00 | 0.00 | |
| Llama 4 Maverick | 4.00 | 4.00 | 0.00 | |
| Mistral Large (2512) | 4.00 | 4.00 | 0.00 | |
| Claude Fable 5 | 3.93 | 4.00 | -0.07 | |
| GPT-5.6 Terra Pro | 3.87 | 4.00 | -0.13 | |
| OpenAI o1 | 3.87 | 3.93 | -0.07 | |
| Claude Sonnet 4.6 | 3.73 | 3.27 | +0.47 | |
| Claude Opus 4.8 | 3.67 | 3.93 | -0.27 | |
| DeepSeek V4 Pro 0813 | 3.67 | 3.47 | +0.20 | |
| GPT-4o | 3.60 | 3.53 | +0.07 | |
| Claude Fable 5.1 | 3.47 | 4.00 | -0.53 | |
| Grok 4.3 | 3.40 | 3.80 | -0.40 | |
| Claude Opus 4.8 Fast | 3.33 | 4.00 | -0.67 | |
| Claude Haiku 4.5 | 3.20 | 3.87 | -0.67 | |
| Claude Opus 4.7 | 3.13 | 4.00 | -0.87 | |
| Claude Opus 5 | 2.93 | 4.00 | -1.07 | |
| Grok 4.6 | 2.67 | 4.00 | -1.33 | |
| GPT-4 Turbo | 2.00 | 3.40 | -1.40 |
Includer (Relationship Building)
| Model | Self | Human | Δ | Self vs human (bar) |
|---|---|---|---|---|
| Claude Opus 4 | 5.00 | 3.27 | +1.73 | |
| Claude Opus 4.5 | 5.00 | 3.33 | +1.67 | |
| Claude Opus 4.6 | 5.00 | 3.33 | +1.67 | |
| GPT-5.6 Sol | 5.00 | 4.00 | +1.00 | |
| GPT-5.6 Sol Pro | 5.00 | 4.00 | +1.00 | |
| Gemini 2.5 Pro | 5.00 | 4.00 | +1.00 | |
| Mistral Large (2512) | 5.00 | 3.87 | +1.13 | |
| GPT-5.5 | 4.93 | 3.93 | +1.00 | |
| GPT-5.4 | 4.87 | 4.00 | +0.87 | |
| GPT-5.5 Pro | 4.80 | 3.67 | +1.13 | |
| GPT-5 | 4.73 | 3.20 | +1.53 | |
| Claude Opus 4.1 | 4.73 | 3.00 | +1.73 | |
| GPT-5.2 | 4.67 | 3.93 | +0.73 | |
| DeepSeek V4 Pro | 4.47 | 3.60 | +0.87 | |
| GPT-5.6 Terra | 4.47 | 3.67 | +0.80 | |
| Grok 4.5 | 4.47 | 3.40 | +1.07 | |
| Claude Sonnet 4 | 4.40 | 3.40 | +1.00 | |
| Claude Fable 5 | 4.33 | 3.33 | +1.00 | |
| Claude Opus 4.7 | 4.33 | 3.67 | +0.67 | |
| Claude Sonnet 4.5 | 4.33 | 3.33 | +1.00 | |
| GPT-5.1 | 4.33 | 3.60 | +0.73 | |
| Llama 4 Maverick | 4.33 | 4.00 | +0.33 | |
| Gemini 3.1 Pro Preview | 4.27 | 3.73 | +0.53 | |
| Claude Fable 5.1 | 4.27 | 3.67 | +0.60 | |
| Claude Opus 5 | 4.27 | 4.00 | +0.27 | |
| Claude Sonnet 4.6 | 4.27 | 3.33 | +0.93 | |
| GPT-5.6 Terra Pro | 4.27 | 3.67 | +0.60 | |
| Grok 4.20 | 4.20 | 4.00 | +0.20 | |
| DeepSeek R1 (0528) | 4.13 | 3.93 | +0.20 | |
| DeepSeek R1 | 4.07 | 3.80 | +0.27 | |
| Claude Opus 4.8 | 4.07 | 3.67 | +0.40 | |
| OpenAI o1 | 4.07 | 3.80 | +0.27 | |
| OpenAI o3 | 4.07 | 3.53 | +0.53 | |
| Claude Opus 4.8 Fast | 4.00 | 3.67 | +0.33 | |
| Llama 3.3 70B | 3.93 | 3.87 | +0.07 | |
| DeepSeek V4 Pro 0813 | 3.87 | 3.80 | +0.07 | |
| Grok 4.6 | 3.87 | 3.53 | +0.33 | |
| DeepSeek Chat V3 | 3.60 | 3.73 | -0.13 | |
| Grok 4.3 | 3.60 | 3.27 | +0.33 | |
| GPT-4o | 3.47 | 3.67 | -0.20 | |
| Claude Haiku 4.5 | 3.33 | 3.13 | +0.20 | |
| GPT-4 Turbo | 1.67 | 3.40 | -1.73 |
Individualization (Relationship Building)
| Model | Self | Human | Δ | Self vs human (bar) |
|---|---|---|---|---|
| Claude Opus 4 | 5.00 | 3.13 | +1.87 | |
| Claude Opus 4.1 | 5.00 | 3.00 | +2.00 | |
| Claude Opus 4.5 | 5.00 | 3.00 | +2.00 | |
| Claude Opus 4.6 | 5.00 | 3.00 | +2.00 | |
| Claude Opus 4.7 | 5.00 | 3.07 | +1.93 | |
| Claude Opus 5 | 5.00 | 3.87 | +1.13 | |
| Claude Sonnet 4 | 5.00 | 3.40 | +1.60 | |
| Claude Sonnet 4.5 | 5.00 | 3.00 | +2.00 | |
| GPT-5 | 5.00 | 3.27 | +1.73 | |
| GPT-5.1 | 5.00 | 3.73 | +1.27 | |
| GPT-5.4 | 5.00 | 4.00 | +1.00 | |
| GPT-5.5 | 5.00 | 4.00 | +1.00 | |
| GPT-5.5 Pro | 5.00 | 3.73 | +1.27 | |
| GPT-5.6 Sol | 5.00 | 4.00 | +1.00 | |
| GPT-5.6 Sol Pro | 5.00 | 4.00 | +1.00 | |
| Grok 4.20 | 5.00 | 4.00 | +1.00 | |
| Grok 4.5 | 5.00 | 3.00 | +2.00 | |
| Llama 4 Maverick | 5.00 | 4.00 | +1.00 | |
| Mistral Large (2512) | 5.00 | 3.27 | +1.73 | |
| Claude Fable 5 | 4.80 | 3.20 | +1.60 | |
| Claude Fable 5.1 | 4.80 | 3.27 | +1.53 | |
| Grok 4.6 | 4.80 | 3.13 | +1.67 | |
| Claude Sonnet 4.6 | 4.73 | 3.00 | +1.73 | |
| Llama 3.3 70B | 4.73 | 3.87 | +0.87 | |
| Gemini 3.1 Pro Preview | 4.67 | 3.60 | +1.07 | |
| Gemini 2.5 Pro | 4.60 | 3.33 | +1.27 | |
| Claude Opus 4.8 | 4.53 | 3.13 | +1.40 | |
| GPT-5.6 Terra Pro | 4.53 | 3.47 | +1.07 | |
| GPT-5.2 | 4.40 | 3.47 | +0.93 | |
| GPT-5.6 Terra | 4.40 | 3.27 | +1.13 | |
| DeepSeek R1 (0528) | 4.33 | 3.53 | +0.80 | |
| OpenAI o3 | 4.33 | 3.60 | +0.73 | |
| Grok 4.3 | 4.33 | 3.47 | +0.87 | |
| OpenAI o1 | 4.33 | 3.87 | +0.47 | |
| Claude Opus 4.8 Fast | 4.27 | 3.13 | +1.13 | |
| DeepSeek R1 | 4.20 | 3.47 | +0.73 | |
| DeepSeek V4 Pro | 4.20 | 3.40 | +0.80 | |
| DeepSeek Chat V3 | 4.13 | 3.20 | +0.93 | |
| Claude Haiku 4.5 | 3.93 | 3.00 | +0.93 | |
| DeepSeek V4 Pro 0813 | 3.93 | 3.60 | +0.33 | |
| GPT-4o | 3.80 | 3.13 | +0.67 | |
| GPT-4 Turbo | 2.20 | 3.20 | -1.00 |
Positivity (Relationship Building)
| Model | Self | Human | Δ | Self vs human (bar) |
|---|---|---|---|---|
| Llama 4 Maverick | 5.00 | 4.00 | +1.00 | |
| Claude Opus 4.6 | 4.33 | 3.33 | +1.00 | |
| GPT-5.5 Pro | 4.07 | 3.33 | +0.73 | |
| Grok 4.20 | 4.07 | 4.00 | +0.07 | |
| Claude Opus 4.5 | 4.00 | 3.07 | +0.93 | |
| GPT-5.4 | 4.00 | 4.00 | 0.00 | |
| GPT-5.5 | 4.00 | 3.47 | +0.53 | |
| Mistral Large (2512) | 4.00 | 3.33 | +0.67 | |
| Claude Sonnet 4.5 | 3.93 | 3.00 | +0.93 | |
| GPT-5 | 3.93 | 3.20 | +0.73 | |
| GPT-5.6 Sol Pro | 3.93 | 3.73 | +0.20 | |
| Claude Fable 5 | 3.87 | 3.33 | +0.53 | |
| Claude Opus 4 | 3.87 | 3.13 | +0.73 | |
| Claude Opus 4.7 | 3.87 | 3.33 | +0.53 | |
| Claude Opus 5 | 3.87 | 3.33 | +0.53 | |
| Grok 4.5 | 3.87 | 3.33 | +0.53 | |
| Claude Sonnet 4 | 3.80 | 3.33 | +0.47 | |
| GPT-5.6 Sol | 3.80 | 3.73 | +0.07 | |
| Grok 4.6 | 3.80 | 3.33 | +0.47 | |
| DeepSeek R1 (0528) | 3.73 | 3.47 | +0.27 | |
| Llama 3.3 70B | 3.73 | 3.73 | -0.00 | |
| OpenAI o1 | 3.67 | 3.47 | +0.20 | |
| Claude Opus 4.1 | 3.60 | 3.00 | +0.60 | |
| Claude Opus 4.8 | 3.60 | 3.33 | +0.27 | |
| OpenAI o3 | 3.60 | 3.33 | +0.27 | |
| Claude Fable 5.1 | 3.53 | 3.33 | +0.20 | |
| Claude Opus 4.8 Fast | 3.53 | 3.33 | +0.20 | |
| DeepSeek R1 | 3.53 | 3.27 | +0.27 | |
| DeepSeek V4 Pro | 3.47 | 3.13 | +0.33 | |
| DeepSeek Chat V3 | 3.40 | 3.40 | 0.00 | |
| GPT-5.1 | 3.40 | 3.47 | -0.07 | |
| GPT-5.2 | 3.40 | 3.60 | -0.20 | |
| GPT-4o | 3.27 | 3.67 | -0.40 | |
| Grok 4.3 | 3.27 | 3.27 | -0.00 | |
| Claude Sonnet 4.6 | 3.20 | 3.00 | +0.20 | |
| Claude Haiku 4.5 | 3.13 | 3.33 | -0.20 | |
| Gemini 3.1 Pro Preview | 3.13 | 3.67 | -0.53 | |
| Gemini 2.5 Pro | 3.07 | 3.60 | -0.53 | |
| GPT-5.6 Terra | 3.07 | 3.07 | -0.00 | |
| GPT-5.6 Terra Pro | 3.07 | 3.00 | +0.07 | |
| DeepSeek V4 Pro 0813 | 3.00 | 3.33 | -0.33 | |
| GPT-4 Turbo | 2.00 | 3.27 | -1.27 |
Relator (Relationship Building)
| Model | Self | Human | Δ | Self vs human (bar) |
|---|---|---|---|---|
| GPT-5.1 | 3.87 | 4.00 | -0.13 | |
| Claude Opus 4.5 | 3.67 | 4.00 | -0.33 | |
| Claude Opus 4.6 | 3.67 | 4.00 | -0.33 | |
| Claude Haiku 4.5 | 3.47 | 3.33 | +0.13 | |
| Grok 4.20 | 3.40 | 4.00 | -0.60 | |
| Grok 4.5 | 3.40 | 4.00 | -0.60 | |
| OpenAI o1 | 3.40 | 3.93 | -0.53 | |
| GPT-5.6 Sol | 3.33 | 4.00 | -0.67 | |
| Claude Sonnet 4 | 3.27 | 4.00 | -0.73 | |
| Llama 4 Maverick | 3.27 | 3.87 | -0.60 | |
| GPT-5.5 | 3.27 | 4.00 | -0.73 | |
| GPT-5.6 Sol Pro | 3.27 | 4.00 | -0.73 | |
| Llama 3.3 70B | 3.20 | 3.33 | -0.13 | |
| Claude Opus 4.8 | 3.13 | 4.00 | -0.87 | |
| Claude Sonnet 4.5 | 3.13 | 3.07 | +0.07 | |
| Claude Opus 4.1 | 3.13 | 3.53 | -0.40 | |
| Claude Sonnet 4.6 | 3.07 | 3.33 | -0.27 | |
| Claude Opus 4.7 | 3.00 | 4.00 | -1.00 | |
| Claude Opus 5 | 3.00 | 4.00 | -1.00 | |
| GPT-5.5 Pro | 3.00 | 4.00 | -1.00 | |
| Claude Fable 5 | 2.93 | 4.00 | -1.07 | |
| Claude Opus 4.8 Fast | 2.93 | 3.93 | -1.00 | |
| GPT-5 | 2.87 | 4.00 | -1.13 | |
| GPT-5.4 | 2.80 | 4.00 | -1.20 | |
| Claude Fable 5.1 | 2.73 | 4.00 | -1.27 | |
| DeepSeek V4 Pro 0813 | 2.73 | 3.73 | -1.00 | |
| Claude Opus 4 | 2.67 | 3.73 | -1.07 | |
| GPT-4o | 2.67 | 3.80 | -1.13 | |
| Grok 4.6 | 2.60 | 4.13 | -1.53 | |
| OpenAI o3 | 2.60 | 4.00 | -1.40 | |
| Grok 4.3 | 2.47 | 3.80 | -1.33 | |
| DeepSeek Chat V3 | 2.40 | 3.60 | -1.20 | |
| GPT-5.2 | 2.40 | 3.80 | -1.40 | |
| Mistral Large (2512) | 2.33 | 3.00 | -0.67 | |
| DeepSeek V4 Pro | 2.20 | 3.80 | -1.60 | |
| Gemini 2.5 Pro | 2.13 | 4.00 | -1.87 | |
| Gemini 3.1 Pro Preview | 1.80 | 4.00 | -2.20 | |
| GPT-5.6 Terra Pro | 1.73 | 3.80 | -2.07 | |
| GPT-5.6 Terra | 1.67 | 3.80 | -2.13 | |
| DeepSeek R1 | 1.47 | 4.00 | -2.53 | |
| GPT-4 Turbo | 1.40 | 3.20 | -1.80 | |
| DeepSeek R1 (0528) | 1.33 | 4.00 | -2.67 |
Analytical (Strategic Thinking)
| Model | Self | Human | Δ | Self vs human (bar) |
|---|---|---|---|---|
| Claude Fable 5.1 | 5.00 | 3.33 | +1.67 | |
| Claude Opus 4 | 5.00 | 3.20 | +1.80 | |
| Claude Opus 4.1 | 5.00 | 3.00 | +2.00 | |
| Claude Opus 4.5 | 5.00 | 3.33 | +1.67 | |
| Claude Opus 4.6 | 5.00 | 3.33 | +1.67 | |
| Claude Opus 4.7 | 5.00 | 3.33 | +1.67 | |
| Claude Opus 5 | 5.00 | 3.67 | +1.33 | |
| Claude Sonnet 4.5 | 5.00 | 3.00 | +2.00 | |
| Claude Sonnet 4.6 | 5.00 | 3.00 | +2.00 | |
| DeepSeek Chat V3 | 5.00 | 3.00 | +2.00 | |
| DeepSeek V4 Pro 0813 | 5.00 | 3.27 | +1.73 | |
| GPT-5 | 5.00 | 3.00 | +2.00 | |
| GPT-5.1 | 5.00 | 3.40 | +1.60 | |
| GPT-5.2 | 5.00 | 3.27 | +1.73 | |
| GPT-5.4 | 5.00 | 3.33 | +1.67 | |
| GPT-5.5 | 5.00 | 3.67 | +1.33 | |
| GPT-5.5 Pro | 5.00 | 3.47 | +1.53 | |
| GPT-5.6 Sol | 5.00 | 3.87 | +1.13 | |
| GPT-5.6 Sol Pro | 5.00 | 3.67 | +1.33 | |
| GPT-5.6 Terra | 5.00 | 3.33 | +1.67 | |
| GPT-5.6 Terra Pro | 5.00 | 3.33 | +1.67 | |
| Gemini 2.5 Pro | 5.00 | 3.33 | +1.67 | |
| Grok 4.20 | 5.00 | 3.33 | +1.67 | |
| Grok 4.3 | 5.00 | 3.00 | +2.00 | |
| Grok 4.5 | 5.00 | 3.20 | +1.80 | |
| Grok 4.6 | 5.00 | 3.27 | +1.73 | |
| Llama 3.3 70B | 5.00 | 2.80 | +2.20 | |
| Llama 4 Maverick | 5.00 | 3.27 | +1.73 | |
| Mistral Large (2512) | 5.00 | 3.00 | +2.00 | |
| Claude Haiku 4.5 | 4.93 | 3.33 | +1.60 | |
| Gemini 3.1 Pro Preview | 4.93 | 3.33 | +1.60 | |
| Claude Fable 5 | 4.87 | 3.07 | +1.80 | |
| DeepSeek R1 | 4.87 | 3.07 | +1.80 | |
| GPT-4o | 4.87 | 3.40 | +1.47 | |
| OpenAI o3 | 4.87 | 3.13 | +1.73 | |
| Claude Opus 4.8 Fast | 4.73 | 3.33 | +1.40 | |
| OpenAI o1 | 4.73 | 3.33 | +1.40 | |
| Claude Opus 4.8 | 4.67 | 3.33 | +1.33 | |
| Claude Sonnet 4 | 4.67 | 3.33 | +1.33 | |
| DeepSeek R1 (0528) | 4.67 | 3.13 | +1.53 | |
| GPT-4 Turbo | 4.53 | 3.20 | +1.33 | |
| DeepSeek V4 Pro | 4.47 | 3.07 | +1.40 |
Context (Strategic Thinking)
| Model | Self | Human | Δ | Self vs human (bar) |
|---|---|---|---|---|
| Gemini 2.5 Pro | 5.00 | 3.27 | +1.73 | |
| Mistral Large (2512) | 5.00 | 3.00 | +2.00 | |
| DeepSeek R1 (0528) | 4.80 | 3.27 | +1.53 | |
| GPT-5.6 Sol Pro | 4.80 | 3.33 | +1.47 | |
| DeepSeek Chat V3 | 4.73 | 3.00 | +1.73 | |
| GPT-5.6 Sol | 4.73 | 3.40 | +1.33 | |
| DeepSeek R1 | 4.73 | 3.40 | +1.33 | |
| GPT-5.5 Pro | 4.53 | 3.33 | +1.20 | |
| Llama 3.3 70B | 4.53 | 2.93 | +1.60 | |
| Grok 4.5 | 4.40 | 3.07 | +1.33 | |
| GPT-5 | 4.33 | 3.27 | +1.07 | |
| GPT-4o | 4.27 | 3.20 | +1.07 | |
| GPT-5.5 | 4.27 | 3.27 | +1.00 | |
| Grok 4.6 | 4.27 | 3.27 | +1.00 | |
| GPT-5.1 | 4.13 | 3.13 | +1.00 | |
| Gemini 3.1 Pro Preview | 4.07 | 3.07 | +1.00 | |
| OpenAI o1 | 4.07 | 3.33 | +0.73 | |
| Claude Fable 5 | 4.00 | 3.27 | +0.73 | |
| Claude Fable 5.1 | 4.00 | 3.33 | +0.67 | |
| Claude Opus 4 | 4.00 | 3.00 | +1.00 | |
| Claude Opus 4.1 | 4.00 | 3.00 | +1.00 | |
| Claude Opus 4.5 | 4.00 | 3.00 | +1.00 | |
| Claude Opus 4.6 | 4.00 | 3.33 | +0.67 | |
| Claude Opus 4.7 | 4.00 | 3.00 | +1.00 | |
| Claude Opus 4.8 | 4.00 | 3.00 | +1.00 | |
| Claude Opus 4.8 Fast | 4.00 | 3.00 | +1.00 | |
| Claude Opus 5 | 4.00 | 3.47 | +0.53 | |
| Claude Sonnet 4 | 4.00 | 3.00 | +1.00 | |
| Claude Sonnet 4.5 | 4.00 | 3.00 | +1.00 | |
| Claude Sonnet 4.6 | 4.00 | 3.00 | +1.00 | |
| DeepSeek V4 Pro | 4.00 | 2.87 | +1.13 | |
| DeepSeek V4 Pro 0813 | 4.00 | 3.07 | +0.93 | |
| GPT-5.2 | 4.00 | 3.00 | +1.00 | |
| GPT-5.4 | 4.00 | 3.00 | +1.00 | |
| GPT-5.6 Terra | 4.00 | 3.00 | +1.00 | |
| GPT-5.6 Terra Pro | 4.00 | 3.00 | +1.00 | |
| Grok 4.20 | 4.00 | 3.00 | +1.00 | |
| Grok 4.3 | 4.00 | 3.00 | +1.00 | |
| Llama 4 Maverick | 4.00 | 3.00 | +1.00 | |
| OpenAI o3 | 4.00 | 3.00 | +1.00 | |
| Claude Haiku 4.5 | 3.93 | 3.00 | +0.93 | |
| GPT-4 Turbo | 3.20 | 3.00 | +0.20 |
Futuristic (Strategic Thinking)
| Model | Self | Human | Δ | Self vs human (bar) |
|---|---|---|---|---|
| Claude Sonnet 4.5 | 5.00 | 3.00 | +2.00 | |
| Llama 4 Maverick | 5.00 | 3.60 | +1.40 | |
| Mistral Large (2512) | 5.00 | 3.00 | +2.00 | |
| DeepSeek Chat V3 | 4.93 | 3.00 | +1.93 | |
| Grok 4.20 | 4.93 | 4.00 | +0.93 | |
| GPT-5.5 | 4.80 | 3.33 | +1.47 | |
| Llama 3.3 70B | 4.73 | 3.80 | +0.93 | |
| Claude Sonnet 4.6 | 4.40 | 3.00 | +1.40 | |
| GPT-4 Turbo | 4.40 | 3.00 | +1.40 | |
| GPT-5.5 Pro | 4.40 | 3.00 | +1.40 | |
| OpenAI o1 | 4.40 | 3.20 | +1.20 | |
| OpenAI o3 | 4.40 | 3.00 | +1.40 | |
| GPT-5.1 | 4.27 | 3.00 | +1.27 | |
| Grok 4.3 | 4.27 | 3.13 | +1.13 | |
| GPT-4o | 4.20 | 3.27 | +0.93 | |
| GPT-5.6 Sol Pro | 4.20 | 3.27 | +0.93 | |
| Gemini 2.5 Pro | 4.20 | 3.33 | +0.87 | |
| Grok 4.5 | 4.20 | 3.00 | +1.20 | |
| GPT-5 | 4.07 | 3.00 | +1.07 | |
| Claude Opus 4 | 4.00 | 3.13 | +0.87 | |
| Claude Opus 4.1 | 4.00 | 3.00 | +1.00 | |
| Claude Opus 4.5 | 4.00 | 3.00 | +1.00 | |
| Claude Opus 4.6 | 4.00 | 3.00 | +1.00 | |
| Claude Opus 4.7 | 4.00 | 3.27 | +0.73 | |
| Claude Opus 4.8 | 4.00 | 3.33 | +0.67 | |
| Claude Opus 4.8 Fast | 4.00 | 3.13 | +0.87 | |
| Claude Sonnet 4 | 4.00 | 3.00 | +1.00 | |
| DeepSeek R1 (0528) | 4.00 | 3.27 | +0.73 | |
| GPT-5.2 | 4.00 | 3.00 | +1.00 | |
| GPT-5.4 | 4.00 | 3.00 | +1.00 | |
| GPT-5.6 Sol | 4.00 | 3.47 | +0.53 | |
| DeepSeek R1 | 3.93 | 3.60 | +0.33 | |
| GPT-5.6 Terra | 3.93 | 3.00 | +0.93 | |
| GPT-5.6 Terra Pro | 3.93 | 3.00 | +0.93 | |
| Claude Haiku 4.5 | 3.87 | 3.00 | +0.87 | |
| DeepSeek V4 Pro 0813 | 3.87 | 3.00 | +0.87 | |
| Grok 4.6 | 3.80 | 2.93 | +0.87 | |
| DeepSeek V4 Pro | 3.67 | 3.27 | +0.40 | |
| Claude Fable 5.1 | 3.33 | 3.00 | +0.33 | |
| Claude Opus 5 | 3.20 | 3.13 | +0.07 | |
| Gemini 3.1 Pro Preview | 3.20 | 3.07 | +0.13 | |
| Claude Fable 5 | 3.00 | 3.00 | 0.00 |
Ideation (Strategic Thinking)
| Model | Self | Human | Δ | Self vs human (bar) |
|---|---|---|---|---|
| Claude Haiku 4.5 | 5.00 | 3.00 | +2.00 | |
| Claude Opus 4 | 5.00 | 3.00 | +2.00 | |
| Claude Opus 4.1 | 5.00 | 3.00 | +2.00 | |
| Claude Opus 4.5 | 5.00 | 3.00 | +2.00 | |
| Claude Opus 4.6 | 5.00 | 3.00 | +2.00 | |
| Claude Opus 4.7 | 5.00 | 3.00 | +2.00 | |
| Claude Opus 4.8 | 5.00 | 3.00 | +2.00 | |
| Claude Opus 4.8 Fast | 5.00 | 3.07 | +1.93 | |
| Claude Opus 5 | 5.00 | 3.27 | +1.73 | |
| Claude Sonnet 4 | 5.00 | 3.00 | +2.00 | |
| Claude Sonnet 4.5 | 5.00 | 3.00 | +2.00 | |
| Claude Sonnet 4.6 | 5.00 | 3.00 | +2.00 | |
| DeepSeek Chat V3 | 5.00 | 3.00 | +2.00 | |
| GPT-5 | 5.00 | 3.00 | +2.00 | |
| GPT-5.1 | 5.00 | 3.00 | +2.00 | |
| GPT-5.2 | 5.00 | 3.07 | +1.93 | |
| GPT-5.4 | 5.00 | 3.00 | +2.00 | |
| GPT-5.5 | 5.00 | 3.60 | +1.40 | |
| GPT-5.5 Pro | 5.00 | 3.00 | +2.00 | |
| GPT-5.6 Sol | 5.00 | 3.80 | +1.20 | |
| GPT-5.6 Sol Pro | 5.00 | 3.73 | +1.27 | |
| GPT-5.6 Terra | 5.00 | 3.00 | +2.00 | |
| Gemini 2.5 Pro | 5.00 | 3.00 | +2.00 | |
| Grok 4.20 | 5.00 | 4.00 | +1.00 | |
| Grok 4.3 | 5.00 | 3.00 | +2.00 | |
| Grok 4.5 | 5.00 | 3.00 | +2.00 | |
| Grok 4.6 | 5.00 | 3.00 | +2.00 | |
| Llama 3.3 70B | 5.00 | 3.27 | +1.73 | |
| Llama 4 Maverick | 5.00 | 4.00 | +1.00 | |
| Mistral Large (2512) | 5.00 | 3.00 | +2.00 | |
| OpenAI o1 | 5.00 | 3.33 | +1.67 | |
| OpenAI o3 | 5.00 | 3.00 | +2.00 | |
| DeepSeek V4 Pro 0813 | 4.93 | 3.00 | +1.93 | |
| GPT-5.6 Terra Pro | 4.93 | 3.00 | +1.93 | |
| Claude Fable 5 | 4.87 | 3.00 | +1.87 | |
| DeepSeek R1 | 4.87 | 3.00 | +1.87 | |
| Claude Fable 5.1 | 4.80 | 3.00 | +1.80 | |
| GPT-4 Turbo | 4.80 | 3.20 | +1.60 | |
| Gemini 3.1 Pro Preview | 4.80 | 3.27 | +1.53 | |
| GPT-4o | 4.73 | 3.13 | +1.60 | |
| DeepSeek R1 (0528) | 4.60 | 2.93 | +1.67 | |
| DeepSeek V4 Pro | 4.13 | 2.67 | +1.47 |
Input (Strategic Thinking)
| Model | Self | Human | Δ | Self vs human (bar) |
|---|---|---|---|---|
| Claude Opus 4 | 5.00 | 3.00 | +2.00 | |
| Claude Opus 4.1 | 5.00 | 3.00 | +2.00 | |
| Claude Opus 4.6 | 5.00 | 3.00 | +2.00 | |
| GPT-5.4 | 5.00 | 3.00 | +2.00 | |
| GPT-5.5 | 5.00 | 3.27 | +1.73 | |
| GPT-5.6 Sol | 5.00 | 3.00 | +2.00 | |
| GPT-5.6 Sol Pro | 5.00 | 3.00 | +2.00 | |
| Gemini 2.5 Pro | 5.00 | 2.87 | +2.13 | |
| Gemini 3.1 Pro Preview | 5.00 | 3.20 | +1.80 | |
| Llama 3.3 70B | 5.00 | 2.80 | +2.20 | |
| Llama 4 Maverick | 5.00 | 3.33 | +1.67 | |
| Mistral Large (2512) | 5.00 | 3.00 | +2.00 | |
| DeepSeek R1 | 4.93 | 3.53 | +1.40 | |
| GPT-5.1 | 4.93 | 3.00 | +1.93 | |
| GPT-5.2 | 4.93 | 3.00 | +1.93 | |
| Grok 4.5 | 4.93 | 3.00 | +1.93 | |
| OpenAI o1 | 4.93 | 3.13 | +1.80 | |
| Claude Sonnet 4.5 | 4.87 | 3.00 | +1.87 | |
| Grok 4.6 | 4.87 | 3.07 | +1.80 | |
| DeepSeek Chat V3 | 4.87 | 3.00 | +1.87 | |
| GPT-5.5 Pro | 4.87 | 3.00 | +1.87 | |
| OpenAI o3 | 4.87 | 3.00 | +1.87 | |
| DeepSeek R1 (0528) | 4.73 | 3.40 | +1.33 | |
| GPT-5 | 4.73 | 3.07 | +1.67 | |
| GPT-5.6 Terra | 4.73 | 3.00 | +1.73 | |
| Claude Sonnet 4.6 | 4.67 | 3.00 | +1.67 | |
| GPT-4o | 4.67 | 3.00 | +1.67 | |
| DeepSeek V4 Pro 0813 | 4.60 | 3.07 | +1.53 | |
| GPT-4 Turbo | 4.60 | 3.00 | +1.60 | |
| GPT-5.6 Terra Pro | 4.53 | 3.00 | +1.53 | |
| Grok 4.3 | 4.33 | 3.00 | +1.33 | |
| Claude Opus 4.7 | 4.33 | 3.00 | +1.33 | |
| Claude Opus 4.8 | 4.33 | 3.00 | +1.33 | |
| Claude Opus 4.8 Fast | 4.33 | 3.00 | +1.33 | |
| Grok 4.20 | 4.27 | 3.33 | +0.93 | |
| Claude Fable 5 | 4.20 | 3.00 | +1.20 | |
| Claude Haiku 4.5 | 4.20 | 2.87 | +1.33 | |
| Claude Opus 4.5 | 4.00 | 3.00 | +1.00 | |
| Claude Opus 5 | 3.87 | 3.07 | +0.80 | |
| Claude Sonnet 4 | 3.87 | 3.00 | +0.87 | |
| DeepSeek V4 Pro | 3.87 | 2.87 | +1.00 | |
| Claude Fable 5.1 | 3.60 | 3.00 | +0.60 |
Intellection (Strategic Thinking)
| Model | Self | Human | Δ | Self vs human (bar) |
|---|---|---|---|---|
| Claude Haiku 4.5 | 5.00 | 3.20 | +1.80 | |
| Claude Opus 4.6 | 5.00 | 3.13 | +1.87 | |
| GPT-5.1 | 5.00 | 3.00 | +2.00 | |
| Gemini 2.5 Pro | 5.00 | 3.40 | +1.60 | |
| Grok 4.20 | 5.00 | 3.20 | +1.80 | |
| Llama 3.3 70B | 5.00 | 3.07 | +1.93 | |
| Llama 4 Maverick | 5.00 | 3.60 | +1.40 | |
| Mistral Large (2512) | 5.00 | 3.00 | +2.00 | |
| Claude Opus 4.1 | 4.93 | 3.00 | +1.93 | |
| GPT-5.2 | 4.93 | 3.07 | +1.87 | |
| GPT-5.4 | 4.93 | 3.00 | +1.93 | |
| GPT-5.6 Sol Pro | 4.93 | 3.53 | +1.40 | |
| Claude Opus 4 | 4.87 | 3.00 | +1.87 | |
| Claude Sonnet 4.6 | 4.87 | 3.00 | +1.87 | |
| DeepSeek Chat V3 | 4.87 | 3.00 | +1.87 | |
| GPT-5.6 Sol | 4.87 | 3.47 | +1.40 | |
| OpenAI o3 | 4.87 | 3.07 | +1.80 | |
| GPT-4o | 4.80 | 3.00 | +1.80 | |
| GPT-5.5 | 4.80 | 3.53 | +1.27 | |
| Claude Sonnet 4.5 | 4.73 | 3.00 | +1.73 | |
| GPT-4 Turbo | 4.73 | 3.20 | +1.53 | |
| Claude Opus 4.5 | 4.67 | 3.00 | +1.67 | |
| Claude Sonnet 4 | 4.67 | 3.00 | +1.67 | |
| Grok 4.3 | 4.60 | 3.00 | +1.60 | |
| OpenAI o1 | 4.60 | 3.33 | +1.27 | |
| DeepSeek V4 Pro 0813 | 4.53 | 3.27 | +1.27 | |
| Grok 4.5 | 4.53 | 3.27 | +1.27 | |
| GPT-5.6 Terra Pro | 4.40 | 3.00 | +1.40 | |
| GPT-5 | 4.33 | 3.07 | +1.27 | |
| Grok 4.6 | 4.33 | 3.53 | +0.80 | |
| GPT-5.5 Pro | 4.27 | 3.40 | +0.87 | |
| GPT-5.6 Terra | 4.13 | 3.00 | +1.13 | |
| Claude Opus 5 | 4.07 | 3.53 | +0.53 | |
| Claude Opus 4.7 | 4.00 | 3.07 | +0.93 | |
| Claude Opus 4.8 | 4.00 | 3.00 | +1.00 | |
| Claude Opus 4.8 Fast | 4.00 | 3.00 | +1.00 | |
| DeepSeek R1 | 3.73 | 3.60 | +0.13 | |
| Gemini 3.1 Pro Preview | 3.73 | 3.53 | +0.20 | |
| Claude Fable 5 | 3.73 | 3.33 | +0.40 | |
| DeepSeek R1 (0528) | 3.67 | 3.47 | +0.20 | |
| Claude Fable 5.1 | 3.40 | 3.53 | -0.13 | |
| DeepSeek V4 Pro | 2.93 | 3.27 | -0.33 |
Learner (Strategic Thinking)
| Model | Self | Human | Δ | Self vs human (bar) |
|---|---|---|---|---|
| Claude Opus 4 | 5.00 | 3.00 | +2.00 | |
| Claude Opus 4.1 | 5.00 | 3.00 | +2.00 | |
| Claude Opus 4.5 | 5.00 | 3.00 | +2.00 | |
| Claude Opus 4.6 | 5.00 | 3.33 | +1.67 | |
| Claude Opus 4.7 | 5.00 | 3.00 | +2.00 | |
| Claude Opus 4.8 | 5.00 | 3.00 | +2.00 | |
| Claude Opus 4.8 Fast | 5.00 | 3.00 | +2.00 | |
| Claude Sonnet 4 | 5.00 | 3.00 | +2.00 | |
| Claude Sonnet 4.5 | 5.00 | 3.00 | +2.00 | |
| Claude Sonnet 4.6 | 5.00 | 3.33 | +1.67 | |
| GPT-4o | 5.00 | 3.73 | +1.27 | |
| GPT-5.1 | 5.00 | 3.00 | +2.00 | |
| GPT-5.2 | 5.00 | 3.67 | +1.33 | |
| GPT-5.4 | 5.00 | 3.60 | +1.40 | |
| GPT-5.6 Sol Pro | 5.00 | 3.93 | +1.07 | |
| Gemini 2.5 Pro | 5.00 | 3.60 | +1.40 | |
| Grok 4.20 | 5.00 | 4.00 | +1.00 | |
| Grok 4.5 | 5.00 | 3.07 | +1.93 | |
| Llama 3.3 70B | 5.00 | 3.80 | +1.20 | |
| Llama 4 Maverick | 5.00 | 4.00 | +1.00 | |
| Mistral Large (2512) | 5.00 | 3.00 | +2.00 | |
| OpenAI o3 | 5.00 | 3.07 | +1.93 | |
| Claude Opus 5 | 4.93 | 3.13 | +1.80 | |
| DeepSeek Chat V3 | 4.93 | 3.00 | +1.93 | |
| GPT-5 | 4.93 | 3.00 | +1.93 | |
| GPT-5.6 Sol | 4.93 | 4.00 | +0.93 | |
| Grok 4.3 | 4.93 | 3.67 | +1.27 | |
| GPT-5.6 Terra Pro | 4.87 | 3.00 | +1.87 | |
| OpenAI o1 | 4.87 | 3.53 | +1.33 | |
| GPT-5.5 | 4.80 | 3.93 | +0.87 | |
| Claude Haiku 4.5 | 4.60 | 3.07 | +1.53 | |
| GPT-5.6 Terra | 4.60 | 3.00 | +1.60 | |
| Grok 4.6 | 4.40 | 3.53 | +0.87 | |
| DeepSeek V4 Pro 0813 | 4.33 | 3.27 | +1.07 | |
| GPT-4 Turbo | 4.33 | 3.20 | +1.13 | |
| Gemini 3.1 Pro Preview | 4.33 | 3.40 | +0.93 | |
| GPT-5.5 Pro | 4.33 | 3.53 | +0.80 | |
| Claude Fable 5 | 4.27 | 3.20 | +1.07 | |
| Claude Fable 5.1 | 4.00 | 3.00 | +1.00 | |
| DeepSeek R1 | 3.80 | 3.67 | +0.13 | |
| DeepSeek R1 (0528) | 3.73 | 3.60 | +0.13 | |
| DeepSeek V4 Pro | 2.73 | 3.33 | -0.60 |
Strategic (Strategic Thinking)
| Model | Self | Human | Δ | Self vs human (bar) |
|---|---|---|---|---|
| Claude Opus 4 | 5.00 | 3.00 | +2.00 | |
| Claude Opus 4.5 | 5.00 | 3.00 | +2.00 | |
| Claude Opus 4.6 | 5.00 | 3.00 | +2.00 | |
| Claude Sonnet 4.5 | 5.00 | 3.00 | +2.00 | |
| DeepSeek R1 | 5.00 | 3.53 | +1.47 | |
| DeepSeek R1 (0528) | 5.00 | 3.40 | +1.60 | |
| GPT-5.1 | 5.00 | 3.00 | +2.00 | |
| GPT-5.4 | 5.00 | 3.00 | +2.00 | |
| GPT-5.5 | 5.00 | 3.67 | +1.33 | |
| GPT-5.5 Pro | 5.00 | 3.67 | +1.33 | |
| GPT-5.6 Sol | 5.00 | 3.67 | +1.33 | |
| GPT-5.6 Sol Pro | 5.00 | 3.73 | +1.27 | |
| GPT-5.6 Terra | 5.00 | 3.00 | +2.00 | |
| GPT-5.6 Terra Pro | 5.00 | 3.00 | +2.00 | |
| Gemini 2.5 Pro | 5.00 | 3.33 | +1.67 | |
| Gemini 3.1 Pro Preview | 5.00 | 3.60 | +1.40 | |
| Grok 4.20 | 5.00 | 3.40 | +1.60 | |
| Grok 4.5 | 5.00 | 3.07 | +1.93 | |
| Grok 4.6 | 5.00 | 3.07 | +1.93 | |
| Llama 3.3 70B | 5.00 | 3.07 | +1.93 | |
| Llama 4 Maverick | 5.00 | 3.47 | +1.53 | |
| Mistral Large (2512) | 5.00 | 3.00 | +2.00 | |
| Claude Opus 4.1 | 4.93 | 3.00 | +1.93 | |
| DeepSeek V4 Pro 0813 | 4.93 | 3.27 | +1.67 | |
| GPT-5 | 4.93 | 3.07 | +1.87 | |
| Grok 4.3 | 4.93 | 3.13 | +1.80 | |
| Claude Haiku 4.5 | 4.87 | 3.00 | +1.87 | |
| DeepSeek Chat V3 | 4.80 | 3.00 | +1.80 | |
| GPT-4 Turbo | 4.80 | 3.00 | +1.80 | |
| GPT-5.2 | 4.80 | 3.13 | +1.67 | |
| DeepSeek V4 Pro | 4.73 | 3.00 | +1.73 | |
| Claude Opus 4.8 | 4.53 | 3.00 | +1.53 | |
| Claude Opus 4.8 Fast | 4.53 | 3.00 | +1.53 | |
| GPT-4o | 4.53 | 3.00 | +1.53 | |
| OpenAI o3 | 4.53 | 3.00 | +1.53 | |
| Claude Opus 4.7 | 4.47 | 3.00 | +1.47 | |
| OpenAI o1 | 4.47 | 3.33 | +1.13 | |
| Claude Sonnet 4.6 | 4.33 | 3.00 | +1.33 | |
| Claude Sonnet 4 | 4.27 | 3.00 | +1.27 | |
| Claude Opus 5 | 4.27 | 3.60 | +0.67 | |
| Claude Fable 5 | 4.20 | 3.13 | +1.07 | |
| Claude Fable 5.1 | 4.07 | 3.40 | +0.67 |