Multilingual Mathematical Reasoning on MMATH All Languages (test)
28.6Average Score (All)Qwen2.5-7B-Instruct + LANG
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| Qwen2.5-7B-Instruct + LANGBackbone=Qwen2.5-7B-Instruct, Method=LANG2026.05 | 28.6 | 28.6 | — | |
| Qwen2.5-7B-Instruct + LC-GRPOBackbone=Qwen2.5-7B-Instruct, Method=LC-GRPO2026.05 | 26.3 | 26.3 | — | |
| Qwen2.5-7B-Instruct + mGRPOBackbone=Qwen2.5-7B-Instruct, Method=mGRPO2026.05 | 26 | 26 | — | |
| Qwen2.5-7B-Instruct + M-ThinkerBackbone=Qwen2.5-7B-Instruct, Method=M-Thinker2026.05 | 24.4 | 24.4 | — | |
| Qwen2.5-7B-InstructBackbone=Qwen2.5-7B-Instruct, Metric Type=Accuracy2026.05 | 23.8 | — | 23.8 | |
| Qwen2.5-7B-Instruct + LCPBackbone=Qwen2.5-7B-Instruct, Method=LCP2026.05 | 21.1 | 21.1 | — | |
| Qwen2.5-7B-Instruct + QRTBackbone=Qwen2.5-7B-Instruct, Method=QRT2026.05 | 20.1 | 20.1 | — | |
| Qwen2.5-7B-Instruct + DITBackbone=Qwen2.5-7B-Instruct, Method=DIT2026.05 | 19.5 | 19.5 | — | |
| Qwen2.5-3B-Instruct + LANGBackbone=Qwen2.5-3B-Instruct, Method=LANG2026.05 | 17.7 | 17.7 | — | |
| Qwen2.5-7B-Instruct + M-SFTBackbone=Qwen2.5-7B-Instruct, Method=M-SFT2026.05 | 17.4 | 17.4 | — | |
| Qwen2.5-3B-Instruct + LC-GRPOBackbone=Qwen2.5-3B-Instruct, Method=LC-GRPO2026.05 | 16.8 | 16.8 | — | |
| Qwen2.5-3B-InstructBackbone=Qwen2.5-3B-Instruct, Metric Type=Accuracy2026.05 | 15.7 | — | 15.7 | |
| Qwen2.5-3B-Instruct + mGRPOBackbone=Qwen2.5-3B-Instruct, Method=mGRPO2026.05 | 15.7 | 15.7 | — | |
| Qwen2.5-3B-Instruct + DITBackbone=Qwen2.5-3B-Instruct, Method=DIT2026.05 | 15.6 | 15.6 | — | |
| Qwen2.5-3B-Instruct + M-SFTBackbone=Qwen2.5-3B-Instruct, Method=M-SFT2026.05 | 15.5 | 15.5 | — | |
| Qwen2.5-3B-Instruct + QRTBackbone=Qwen2.5-3B-Instruct, Method=QRT2026.05 | 15.4 | 15.4 | — | |
| Qwen2.5-3B-Instruct + M-ThinkerBackbone=Qwen2.5-3B-Instruct, Method=M-Thinker2026.05 | 15.3 | 15.3 | — | |
| Qwen2.5-3B-Instruct + LCPBackbone=Qwen2.5-3B-Instruct, Method=LCP2026.05 | 14.8 | 14.8 | — | |
| Qwen2.5-3B-Instruct + Vanilla GRPOBackbone=Qwen2.5-3B-Instruct, Method=Vanilla GRPO2026.05 | 7.3 | 7.3 | — | |
| Qwen2.5-7B-InstructBackbone=Qwen2.5-7B-Instruct, Metric Type=LC&Acc2026.05 | 6 | 6 | — | |
| Qwen2.5-3B-InstructBackbone=Qwen2.5-3B-Instruct, Metric Type=LC&Acc2026.05 | 5.6 | 5.6 | — | |
| Qwen2.5-7B-Instruct + Vanilla GRPOBackbone=Qwen2.5-7B-Instruct, Method=Vanilla GRPO2026.05 | 3.3 | 3.3 | — |