List your company

Math Reasoning on OpenR1

72Pass@8SD-ZERO
54.3258.9163.568.09Apr 13, 2026

Evaluation results

MethodLinks
SD-ZEROBase Model=Qwen3-4B-Instruct2026.0472
RFTBase Model=Qwen3-4B-Instruct2026.0470.2
SRTBase Model=Qwen3-4B-Instruct2026.0470.2
GRPOBase Model=Qwen3-4B-Instruct2026.0470
SDFTBase Model=Qwen3-4B-Instruct2026.0470
GRPOBase Model=Olmo-3-7B-Instruct2026.0470
Qwen3-4B-InstructBase Model=Qwen3-4B-Instruct2026.0469.2
SFTBase Model=Qwen3-4B-Instruct2026.0469.2
SD-ZEROBase Model=Olmo-3-7B-Instruct2026.0468
SRTBase Model=Olmo-3-7B-Instruct2026.0466
RFTBase Model=Olmo-3-7B-Instruct2026.0462
Olmo-3-7B-InstructBase Model=Olmo-3-7B-Instruct2026.0460
SDFTBase Model=Olmo-3-7B-Instruct2026.0458
SFTBase Model=Olmo-3-7B-Instruct2026.0455