Mathematical Reasoning on Average Across all Benchmarks
0.8Delta AccuracyDPOshortest
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| DPOshortestBackbone=R1-Distill-Qwen-1.5B2026.02 | 0.8 | -32.2 | — | |
| RFTshortestBackbone=R1-Distill-Qwen-7B2026.02 | 0.6 | 0.5 | — | |
| RFTshortestBackbone=Qwen3-4B-Thinking2026.02 | 0.2 | -5.9 | — | |
| ConPressBackbone=R1-Distill-Qwen-7B2026.02 | 0 | -33.9 | — | |
| RFTshortestBackbone=R1-Distill-Qwen-1.5B2026.02 | -0.1 | 0.1 | — | |
| ConPressBackbone=R1-Distill-Qwen-1.5B2026.02 | -0.2 | -40.2 | — | |
| ThinkPruneBackbone=R1-Distill-Qwen-1.5B2026.02 | -0.4 | -45.9 | — | |
| ConPressBackbone=Qwen3-4B-Thinking2026.02 | -0.6 | -48.7 | — | |
| TRiMSBackbone=Qwen3-4B2026.03 | -0.63 | -88.3 | 70.6 | |
| AdaptThinkBackbone=R1-Distill-Qwen-1.5B2026.02 | -0.7 | -55.8 | — | |
| DPOshortestBackbone=Qwen3-4B-Thinking2026.02 | -0.9 | -13.1 | — | |
| AdaptThinkBackbone=R1-Distill-Qwen-7B2026.02 | -1.2 | -36.3 | — | |
| LC-R1Backbone=R1-Distill-Qwen-1.5B2026.02 | -1.7 | -53.1 | — | |
| DPOshortestBackbone=R1-Distill-Qwen-7B2026.02 | -2.3 | -31.4 | — | |
| LC-R1Backbone=R1-Distill-Qwen-7B2026.02 | -3.1 | -45.4 | — | |
| VanillaBackbone=Qwen3-4B2026.03 | — | — | 8.8 |