Gemma 4 E4B (Reasoning)

1. #216default of 2240

Leader: Sonnet 5.5 · 1823

1. #203default of 2190.5%

Leader: Gemini 4 · 77.5%

1. #317default of 39320.8%

Leader: GLM 5.2 · 99.1%

1. #214default of 22624.4%

Leader: Opus 5.5 · 66.9%

1. #234default of 3878.3%

Leader: GPT-5.6 Sol · 65.9%

1. #223default of 2381.9%

Leader: Fable 5.1 · 91.4%

1. #198default of 2160.0%

Leader: Sonnet 5.5 · 63.6%

1. #408default of 6108.9

Leader: Opus 5.5 · 57.6

1. #196default of 2101.0%

Leader: Muse Wonder Full (Max) · 32.6%

1. #267default of 288-37

Leader: Opus 5.5 · 1866

1. #215default of 39944.2%

Leader: Grok 4.3 · 83.3%

1. #485default of 5268.6%

Leader: Fable 5.1 · 67.2%

1. #48default of 52669.1%

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

1. #376default of 53957.6%

Leader: GPT-6 Astra · 96.3%

1. #222default of 26551.4%

Leader: Opus 5.5 · 87.7%

1. #370default of 52332.0%

Leader: Kimi K3 · 88.7%

1. #261default of 5290.6%

Leader: Muse Wonder Full (Max) · 32.9%

1. #70default of 3511.0s

Leader: Gemini 2.5 Flash-Lite · 0.3s

1. #341default of 35127.6

Leader: Celeris-1 · 1522.5