Paper Criteria Matching on paper-criteria matching dataset (test)
90.64Insuff. Info ScoreWisModel
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| WisModel2025.12 | 90.64 | 94.54 | 91.82 | 94.38 | 93.7 | |
| Gemini3-Pro2025.12 | 67.4 | 66.8 | 15.9 | 91.1 | 73.23 | |
| GPT-5.12025.12 | 64.3 | 63.1 | 31.4 | 85.4 | 70.81 | |
| DeepSeek-V3.22025.12 | 57.9 | 49.2 | 45 | 87 | 66.82 | |
| Claude-Sonnet-4.52025.12 | 46 | 66.5 | 33.3 | 87 | 70.62 | |
| Qwen3-Max2025.12 | 40.8 | 72 | 44.2 | 87.2 | 72.82 |