List your company

Math on LiC Math

92.9Concat ScoreLlama4-Scout
66.58873.41980.2587.081Oct 21, 2025

Evaluation results

MethodLinks
Llama4-Scout2025.1092.96772.1—
DeepSeek-R12025.1092.967.372.4—
GPT-4o2025.1091.967.973.939.9
Llama3.3-70B2025.1091.861.567—
Phi-42025.1090.452.558.1—
GPT-4.12025.1089.770.778.840.5
Gemini-2.5-Pro2025.1089.364.37246.2
Gemini-2.5-Flash2025.1088.466.174.847
Qwen3-8Bsource=Grattafiori et al.2025.1088.472.882.439.1
GPT4o-mini2025.108858.766.7—
Qwen3-8BFinetuning=SFT, Distillation=Gemini-2.5-Pro2025.1087.475.686.557.4
Claude3.7-Sonnet2025.1087.27080.3—
Qwen3-8BOptimization=RLAAR2025.1087.282.294.380.8
Qwen2.5-7BOptimization=RLAAR2025.1083.479.29577
Qwen2.5-7BFinetuning=SFT, Distillation=Gemini-2.5-Pro2025.1082.760.372.957.2
Qwen2.5-7B2025.1082.259.872.836.1
OLMo22025.1080.146.357.8—
GPT-o32025.108063.178.9—
Claude3-Haiku2025.1076.147.161.9—
Qwen3-1.7BOptimization=RLAAR2025.1070.96084.777.2
Qwen3-1.7Bsource=Grattafiori et al.2025.1067.644.465.726.8