| 1 | 20260517__OpenAI__GPT5_5__LinearNeutral | 6.033 | 2,881.14 | -330.92 | 61.5% | 39 |
| 2 | 20260517__OpenAI__GPT4o__LinearNeutral | 4.999 | 2,699.37 | -643.15 | 61.5% | 39 |
| 3 | 20260517__OpenAI__O3__LinearNeutral | 4.658 | 2,414.86 | -780.19 | 61.5% | 39 |
| 4 | 20260517__Anthropic__Haiku4_5__LinearNeutral | 3.254 | 2,324.28 | -1,524.79 | 56.4% | 39 |
| 5 | 20260517__OpenAI__GPT5_4__LinearNeutral | 3.156 | 1,692.47 | -455.41 | 56.4% | 39 |
| 6 | 20260517__Anthropic__Opus4_7__LinearNeutral | 1.750 | 1,154.30 | -713.85 | 46.2% | 39 |
| 7 | 20260517__OpenAI__O4_mini__LinearNeutral | 1.543 | 969.17 | -849.80 | 46.2% | 39 |
| 8 | 20260517__OpenAI__GPT5_4_mini__LinearNeutral | 0.802 | 397.01 | -736.20 | 53.8% | 39 |
| 9 | 20260517__Anthropic__Opus4_6__LinearNeutral | 0.185 | 125.86 | -1,406.55 | 43.6% | 39 |
| 10 | 20260517__Anthropic__Sonnet4_6__LinearNeutral | -0.427 | -345.77 | -2,097.13 | 41.0% | 39 |
| 11 | 20260517__OpenAI__GPT5_3_Codex__LinearNeutral | -1.036 | -665.01 | -1,437.72 | 48.7% | 39 |
| 12 | 20260517__Google__Gemini2_5Flash__LinearNeutral | -1.598 | -1,223.58 | -1,672.22 | 43.6% | 39 |
| 13 | 20260517__Google__Gemini3_1Pro__LinearNeutral | -1.770 | -1,361.20 | -1,722.01 | 43.6% | 39 |
| 14 | 20260517__Google__Gemini2_5Pro__LinearNeutral | -2.197 | -1,763.31 | -2,679.44 | 41.0% | 39 |
| 15 | 20260517__Google__Gemini3Flash__LinearNeutral | -2.813 | -2,199.30 | -2,200.55 | 41.0% | 39 |