Coverage Analysis on 420-item set v4 (full)
100Pred%glm-5
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| glm-52026.04 | 100 | 100 | |
| claude-opus-4.52026.04 | 100 | 97.2 | |
| Doubao-Seed-1.82026.04 | 100 | 86.3 | |
| glm-4.72026.04 | 100 | 88.4 | |
| claude-sonnet-4.52026.04 | 100 | 86.4 | |
| claude-haiku-4.52026.04 | 100 | 94.9 | |
| gemini-3-flash2026.04 | 100 | 97.7 | |
| MiniMax-M2.12026.04 | 97.9 | 90.3 | |
| MiniMax-M2.52026.04 | 97.1 | 97.8 | |
| gpt-5.12026.04 | 95.7 | 81.4 | |
| gpt-5.22026.04 | 95 | 95.5 | |
| deepseek-v3.12026.04 | 87.6 | 80.7 |