Mathematical Reasoning on Average of Mathematical Reasoning Benchmarks
71.74AccuracyQwen3-8B + ICR
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Qwen3-8B + ICRBackbone=Qwen3-8B, Method=ICR2026.05 | 71.74 | 5,133 | |
| Qwen3-4B + ICRBackbone=Qwen3-4B, Method=ICR2026.05 | 71.33 | 4,716 | |
| Qwen3-8B + GRPOBackbone=Qwen3-8B, Method=GRPO2026.05 | 70.64 | 5,998 | |
| Qwen3-4B + GRPOBackbone=Qwen3-4B, Method=GRPO2026.05 | 69.45 | 5,689 | |
| Qwen3-8BBackbone=Qwen3-8B, Method=Base2026.05 | 68.9 | 9,250 | |
| Qwen3-8B + ICR /w LP-FBackbone=Qwen3-8B, Method=ICR /w LP-F2026.05 | 68.43 | 3,838 | |
| Qwen3-4BBackbone=Qwen3-4B, Method=Base2026.05 | 68.4 | 8,809 | |
| Qwen3-8B + LP-FBackbone=Qwen3-8B, Method=LP-F2026.05 | 67.62 | 4,311 | |
| Qwen3-4B + ICR /w LP-FBackbone=Qwen3-4B, Method=ICR /w LP-F2026.05 | 67.51 | 4,101 | |
| Qwen3-4B + LP-FBackbone=Qwen3-4B, Method=LP-F2026.05 | 66.27 | 4,712 | |
| Qwen3-8B + LC-R1Backbone=Qwen3-8B, Method=LC-R12026.05 | 65.33 | 4,799 | |
| Qwen3-8B + ShorterBetterBackbone=Qwen3-8B, Method=ShorterBetter2026.05 | 65.3 | 4,075 | |
| Qwen3-8B + LP-G (Kimi)Backbone=Qwen3-8B, Method=LP-G (Kimi)2026.05 | 64.43 | 3,967 | |
| DSQW-7B + ICR /w LP-FBackbone=DSQW-7B, Method=ICR /w LP-F2026.05 | 62.62 | 5,058 | |
| DSQW-7B + ICRBackbone=DSQW-7B, Method=ICR2026.05 | 61.65 | 6,448 | |
| DSQW-7B + LP-FBackbone=DSQW-7B, Method=LP-F2026.05 | 61.6 | 5,585 | |
| DSQW-7B + LC-R1Backbone=DSQW-7B, Method=LC-R12026.05 | 61.27 | 5,940 | |
| DSQW-7B + ShorterBetterBackbone=DSQW-7B, Method=ShorterBetter2026.05 | 61.12 | 5,144 | |
| Qwen3-4B + ShorterBetterBackbone=Qwen3-4B, Method=ShorterBetter2026.05 | 60.88 | 3,302 | |
| DSQW-7B + GRPOBackbone=DSQW-7B, Method=GRPO2026.05 | 60.6 | 7,384 | |
| DSQW-7B + LP-G (Kimi)Backbone=DSQW-7B, Method=LP-G (Kimi)2026.05 | 60.58 | 5,792 | |
| Qwen3-4B + LP-G (Kimi)Backbone=Qwen3-4B, Method=LP-G (Kimi)2026.05 | 60.33 | 2,993 | |
| Qwen3-4B + LC-R1Backbone=Qwen3-4B, Method=LC-R12026.05 | 60.18 | 4,420 | |
| DSQW-7BBackbone=DSQW-7B, Method=Base2026.05 | 55.57 | 7,624 |