List your company

Math Reasoning on AIME 25 (accuracy (%))

30Accuracy (%)EGLR-OracleL
-1.26.91523.1Jun 15, 2026

Evaluation results

MethodLinks
EGLR-OracleLModel=Qwen2.5-Math-1.5B-Instruct2026.0630
EGLR-OracleLModel=Qwen2.5-7B-Instruct2026.0626.7
EGLR-OracleLModel=Qwen2.5-14B-Instruct2026.0626.7
EGLR-OracleLModel=Qwen2.5-Math-7B-Instruct2026.0626.7
EGLR (best L)Model=Qwen2.5-14B-Instruct2026.0620
EGLR-SCL (B = 10)Model=Qwen2.5-14B-Instruct2026.0620
EGLR (best L)Model=Qwen2.5-Math-1.5B-Instruct2026.0620
EGLR-SCL (B = 10)Model=Qwen2.5-7B-Instruct2026.0616.7
GreedyModel=Qwen2.5-14B-Instruct2026.0616.7
EGLR-OracleLModel=Qwen2.5-3B-Instruct2026.0613.3
EGLR (best L)Model=Qwen2.5-7B-Instruct2026.0613.3
GreedyModel=Qwen2.5-Math-1.5B-Instruct2026.0613.3
EGLR-SCL (B = 10)Model=Qwen2.5-Math-1.5B-Instruct2026.0613.3
GreedyModel=Qwen2.5-Math-7B-Instruct2026.0613.3
EGLR (best L)Model=Qwen2.5-Math-7B-Instruct2026.0613.3
EGLR-SCL (B = 10)Model=Qwen2.5-Math-7B-Instruct2026.0613.3
GreedyModel=Qwen2.5-7B-Instruct2026.0610
EGLR (best L)Model=Qwen2.5-3B-Instruct2026.066.7
EGLR-SCL (B = 10)Model=Qwen2.5-3B-Instruct2026.066.7
EGLR-SCL (B = 10)Model=Llama-3.1-8B-Instruct2026.066.7
EGLR-OracleLModel=Llama-3.1-8B-Instruct2026.066.7
GreedyModel=Qwen2.5-3B-Instruct2026.063.3
EGLR (best L)Model=Llama-3.1-8B-Instruct2026.063.3
GreedyModel=Qwen2.5-0.5B-Instruct2026.060
EGLR (best L)Model=Qwen2.5-0.5B-Instruct2026.060
EGLR-SCL (B = 10)Model=Qwen2.5-0.5B-Instruct2026.060
EGLR-OracleLModel=Qwen2.5-0.5B-Instruct2026.060
GreedyModel=Llama-3.1-8B-Instruct2026.060
GreedyModel=Mistral-7B-Instruct-v0.32026.060
EGLR (best L)Model=Mistral-7B-Instruct-v0.32026.060
EGLR-SCL (B = 10)Model=Mistral-7B-Instruct-v0.32026.060
EGLR-OracleLModel=Mistral-7B-Instruct-v0.32026.060