List your company

Mathematical Reasoning on AIME 2425

93.54Pass@1Gemini
49.995261.300172.60583.9099Feb 8, 2026

Evaluation results

MethodLinks
GeminiBackbone=Qwen3-235B2026.0293.5418.5
Free()LMBackbone=Qwen3-235B2026.0293.1316.4
VanillaBackbone=Qwen3-235B2026.0292.2921.7
No TrainBackbone=Qwen3-235B2026.0290.6316.2
GeminiBackbone=Qwen3-30B2026.0287.9215.4
Free()LMBackbone=Qwen3-30B2026.0287.9214.5
No TrainBackbone=Qwen3-30B2026.0285.2115.9
VanillaBackbone=Qwen3-30B2026.0283.3314.9
Free()LMBackbone=Qwen3-8B2026.027513
No TrainBackbone=Qwen3-8B2026.0273.3315.3
VanillaBackbone=Qwen3-8B2026.0271.6717.6
GeminiBackbone=Qwen3-8B2026.0271.6713.7
H2OBackbone=Qwen3-8B2026.026017.8
TCBackbone=Qwen3-8B2026.0251.6720.3