Query-document Retrieval on MAIR (20% labeled)
77.08Average ScoreERA
Evaluation results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| ERAModel=Qwen3-8B2026.04 | 77.08 | — | 88.1 | 90.73 | 97.87 | 79.05 | 43.06 | 77.76 | |
| Zero-shotModel=Qwen3-8B2026.04 | 76.22 | — | 87.62 | 90.57 | 96.69 | 76.78 | 43.74 | 76.34 | |
| ERAModel=Qwen3-0.6B2026.04 | 72 | — | 84.48 | 88.03 | 91.77 | 73.48 | 37.39 | 71.9 | |
| ERAModel=OpenAI-large2026.04 | 71.91 | — | 85.36 | 85.09 | 95.67 | 73.6 | 39.01 | 71.25 | |
| Embedding AdapterModel=Qwen3-8B2026.04 | 70.24 | — | 81.84 | 85.47 | 93.12 | 72.58 | 34.82 | 70.31 | |
| Zero-shotModel=Qwen3-0.6B2026.04 | 70.24 | — | 82.39 | 88.53 | 91.87 | 71.11 | 36.58 | 69.01 | |
| Zero-shotModel=OpenAI-large2026.04 | 67.83 | — | 79.05 | 81.56 | 93.28 | 65.66 | 36.62 | 67.58 | |
| ERAModel=OpenAI-small2026.04 | 67.83 | — | 81.18 | 81.18 | 92.02 | 69.25 | 32.9 | 67.85 | |
| ERAModel=BGE-M32026.04 | 64.17 | — | 78.53 | 73.59 | 89.03 | 66.86 | 26.56 | 65.78 | |
| Embedding AdapterModel=Qwen3-0.6B2026.04 | 63.52 | — | 75.18 | 81.86 | 85.36 | 66.96 | 28.84 | 62.22 | |
| Embedding AdapterModel=OpenAI-large2026.04 | 63.25 | — | 74.87 | 77.65 | 87.96 | 58.4 | 33.01 | 62.98 | |
| Zero-shotModel=OpenAI-small2026.04 | 60.99 | — | 74.67 | 75.96 | 88.69 | 62.11 | 27.82 | 59.29 | |
| Embedding AdapterModel=OpenAI-small2026.04 | 57.71 | — | 65.21 | 73.27 | 81.62 | 60.62 | 27.14 | 56.91 | |
| Zero-shotModel=BGE-M32026.04 | 55.5 | — | 69.34 | 68.05 | 84.97 | 58.2 | 20.99 | 54.44 | |
| Embedding AdapterModel=BGE-M32026.04 | 51.49 | — | 63.09 | 65.85 | 75.59 | 56.98 | 19.53 | 49.82 |