Loading page…
| # | Model | Net improvement | Samples |
|---|---|---|---|
| 21 | 2.17%±0.77% | 63,940 | |
| 22 | 1.89%±0.86% | 27,007 | |
| 23 | 1.54%±0.9% | 79,621 | |
| 24 | 1.46%±1.19% | 19,096 | |
| 25 | 0.73%±1.05% | 22,203 | |
| 26 | Qwen3.8 Flash NextAlibaba | 0.4%±0.97% | 30,755 |
| 27 |
| -0.08%±0.88% |
| 28,536 |
| 28 | -0.34%±1.14% | 33,240 |
| 29 | -1.27%±1.32% | 39,399 |
| 30 | -1.76%±1.29% | 24,050 |
| 31 | Muse Spark 1.1Meta | -2.97%±0.65% | 95,367 |
|---|
| 32 | Qwen3.7 MaxAlibaba | -3.12%±0.99% | 37,494 |
|---|
| 33 | Hy3Tencent | -4.69%±1.29% | 26,255 |
|---|
| 34 | -5.38%±0.95% | 37,895 |
| 35 | Qwen3.7 PlusAlibaba | -5.38%±1.28% | 20,606 |
|---|
| 36 | -5.41%±1.13% | 19,631 |
| 37 | Mimo V2.5 ProXiaomi | -5.42%±0.98% | 38,911 |
|---|
| 38 | -5.6%±0.96% | 85,599 |
| 39 | Inkling SmallThinky | -7.09%±1.58% | 12,366 |
|---|
| 40 | InklingThinky | -9.12%±1.06% | 41,981 |
|---|
Dots: score · lines: published uncertainty