Compositionality Estimation on Setting Combination H+R
267.53L(P+) ScoreGemini-2.0
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Gemini-2.02026.04 | 267.53 | 4.07 | 0.43 | |
| DeepSeek-V32026.04 | 207.43 | 5.27 | 9.89 | |
| Gemini-2.52026.04 | 205.53 | 0.73 | 38.98 | |
| DeepSeek-R12026.04 | 187.3 | 3.57 | 27.43 | |
| o1-mini2026.04 | 176.6 | 2.67 | 34.26 | |
| QwQ-Plus2026.04 | 147.6 | 9.83 | 4 | |
| Claude-3.52026.04 | 113.6 | 15.83 | 0 | |
| o3-mini2026.04 | 84.73 | 0.77 | 78.79 | |
| Claude-3.72026.04 | 62.57 | 3.8 | 66.39 | |
| Qwen-Max2026.04 | 58.93 | 13.67 | 6.67 | |
| GPT-4o2026.04 | 58.2 | 15.8 | 0 |