Qwen 3 0.6B

1. #316default of 39321.1%
2. #344none of 39314.6%

Leader: GLM 5.2 · 99.1%

1. #248default of 28212.1%
2. #266none of 2827.3%

Leader: Gemini 3 Pro · 91.7%

1. #377none of 3870.0%
2. #380default of 3870.0%

Leader: GPT-5.6 Sol · 65.9%

1. #594none of 6104.8
2. #598default of 6104.8

Leader: Opus 5.5 · 57.6

1. #379default of 39923.3%
2. #386none of 39921.9%

Leader: Grok 4.3 · 83.3%

1. #509default of 5266.3%
2. #518none of 5264.6%

Leader: Fable 5.1 · 67.2%

1. #419default of 5269.1%
2. #481none of 5266.2%

Leader: MiniCPM5-1B (Non-reasoning) · 99.1%

1. #528default of 53923.9%
2. #531none of 53923.1%

Leader: GPT-6 Astra · 96.3%

1. #271default of 28534.7%
2. #279none of 28523.1%

Leader: Gemini 3 Pro · 89.8%

1. #512none of 5230.0%
2. #515default of 5230.0%

Leader: Kimi K3 · 88.7%

1. #179default of 22818.0%
2. #195none of 22810.3%

Leader: GPT-5.2 · 99.0%

1. #102default of 16275.0%
2. #134none of 16252.1%

Leader: GPT-5 · 99.4%

1. #511none of 5290.0%
2. #515default of 5290.0%

Leader: Muse Wonder Full (Max) · 32.9%