共 50/50 个测试站点,50 个已有复测分数。
playwright-recheck-graphweighted+visible-graph-audit
| # | 徽记 | 模型 | 均分 | 区间 | Loading/15 | Graph/35 | Articles/15 | Visual/20 | Interact/15 |
|---|---|---|---|---|---|---|---|---|---|
| >>> | GLM 5.2 GLM | 85.5 | 72.8-93.8 | 15 | 22.3 | 15 | 18.4 | 14.8 | |
| >> | Qwen3.7 Max Qwen | 82.4 | 66.2-93.8 | 14.4 | 27.7 | 14.5 | 13.4 | 12.4 | |
| > | Kimi K2.7 Code Kimi | 80.3 | 51.6-93.8 | 14.6 | 22.3 | 14.5 | 15.4 | 13.6 | |
| 4 | MiniMax M3 MiniMax | 77.4 | 52.6-95.8 | 14.4 | 16.7 | 14.0 | 18.8 | 13.6 | |
| 5 | DeepSeek V4 Pro DeepSeek | 67.1 | 39.2-96 | 14.6 | 16.4 | 14.5 | 9.8 | 11.9 |
| Round | DeepSeekDeepSeek V4 Pro | KimiKimi K2.7 Code | QwenQwen3.7 Max | GLMGLM 5.2 | MiniMaxMiniMax M3 |
|---|---|---|---|---|---|
| r1 | D 39.2 | B+ 86.8 | C 66.2 | B 77 | B 79 |
| r2 | B+ 86.4 | A 93.8 | B+ 82.4 | B 77 | A 93.8 |
| r3 | D 57.8 | B+ 82.2 | B 76.2 | A- 89 | D 52.6 |
| r4 | C 64.6 | D 51.6 | A 93.8 | A 93 | A 95.8 |
| r5 | A 96 | C+ 68.6 | A 93.8 | A- 91 | B 79 |
| r6 | C+ 74.4 | C 66 | B 80 | A 93 | B 77 |
| r7 | C 64.6 | A 93.8 | A 93.8 | C+ 72.8 | B 79 |
| r8 | C 64.2 | A- 89 | C+ 68.4 | B 77 | B 77 |
| r9 | C 62.4 | A- 89 | A 93.8 | A- 91 | C+ 68.2 |
| r10 | C 61.8 | B+ 82.4 | B 75.4 | A 93.8 | C+ 73 |