List your company

Logical Reasoning on English

98.8BPAGemma-2-9B
27.45645.97864.583.022Feb 2, 2026

Evaluation results

MethodLinks
Gemma-2-9BConfiguration=SFT2026.0298.80.8
Qwen-2.5-7BConfiguration=SFT2026.0298.63.2
Gemma-2-9BConfiguration=Steering2026.0298—
Qwen-3-14BConfiguration=Steering2026.0297.8—
Gemma-3-12BConfiguration=SFT2026.0297.70.7
Ministral-14BConfiguration=Steering2026.0297.6—
Gemma-3-12BConfiguration=Steering2026.0297—
Ministral-14BConfiguration=SFT2026.0296.3-1.3
Mistral-7BConfiguration=Steering2026.0296.1—
Qwen-3-14BConfiguration=SFT2026.0295.8-2
Qwen-2.5-7BConfiguration=Steering2026.0295.4—
Mistral-7BConfiguration=SFT2026.0288.1-8
Gemma-3-12BConfiguration=CoT2026.0286.8-10.2
Qwen-3-14BConfiguration=CoT2026.0283.1-14.7
Qwen-2.5-7BConfiguration=CoT2026.0281.7-13.7
Gemma-3-12BConfiguration=Base Model2026.0279.4—
Ministral-14BConfiguration=CoT2026.0276.2-21.4
Qwen-3-14BConfiguration=Base Model2026.0272.3—
Gemma-2-9BConfiguration=CoT2026.0269.9-28.1
Ministral-14BConfiguration=Base Model2026.0263.9—
Gemma-2-9BConfiguration=Base Model2026.0251.8—
Qwen-2.5-7BConfiguration=Base Model2026.0250.8—
Mistral-7BConfiguration=CoT2026.0234.3-61.8
Mistral-7BConfiguration=Base Model2026.0230.2—