Question Answering on BRIGHT (test)
72.2Accuracy (Biology)TS&RL-Index
Evaluation Results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| TS&RL-IndexGenerator=GPT, Retrieval Method=TS&RL-Index2026.06 | 72.2 | 72.4 | 73.1 | 81 | 80.9 | 71.7 | 71.9 | 74.7 | |
| SPIKEGenerator=GPT, Retrieval Method=SPIKE2026.06 | 72 | 71.9 | 71.2 | 76.7 | 76.3 | 70.4 | 70.4 | 72.7 | |
| TongSearchGenerator=GPT, Retrieval Method=TongSearch2026.06 | 70.8 | 72.2 | 73.3 | 77.1 | 76.6 | 68.6 | 66.2 | 72.1 | |
| RL-IndexGenerator=GPT, Retrieval Method=RL-Index2026.06 | 70.3 | 74.2 | 75 | 76.1 | 83 | 73.1 | 69.4 | 74.4 | |
| SBERTGenerator=GPT, Retrieval Method=SBERT2026.06 | 69.1 | 71.7 | 70.8 | 76.3 | 75 | 68.3 | 69.2 | 71.5 | |
| TongSearchGenerator=Claude, Retrieval Method=TongSearch2026.06 | 68.7 | 64.6 | 69 | 71.6 | 75.2 | 59.1 | 58 | 66.6 | |
| TS&RL-IndexGenerator=Claude, Retrieval Method=TS&RL-Index2026.06 | 68.6 | 63.2 | 69.2 | 73.1 | 74.4 | 61.4 | 61.6 | 67.4 | |
| SPIKEGenerator=Claude, Retrieval Method=SPIKE2026.06 | 65.4 | 59.8 | 64.7 | 69.9 | 70.7 | 56.3 | 57 | 63.4 | |
| TS&RL-IndexGenerator=Llama, Retrieval Method=TS&RL-Index2026.06 | 65 | 57.6 | 62.8 | 65 | 67.1 | 55.1 | 61.3 | 62 | |
| TongSearchGenerator=Llama, Retrieval Method=TongSearch2026.06 | 63.6 | 59.6 | 64.7 | 65.3 | 65.3 | 53.4 | 61.2 | 61.9 | |
| RL-IndexGenerator=Claude, Retrieval Method=RL-Index2026.06 | 61.6 | 64.2 | 63 | 69.5 | 73.8 | 60.2 | 59.7 | 64.6 | |
| SBERTGenerator=Claude, Retrieval Method=SBERT2026.06 | 60.2 | 61.8 | 62.8 | 68.4 | 72.6 | 57.6 | 54.1 | 62.5 | |
| SPIKEGenerator=Llama, Retrieval Method=SPIKE2026.06 | 59.6 | 55.1 | 56.4 | 55.7 | 62.6 | 43 | 51.7 | 54.9 | |
| RL-IndexGenerator=Llama, Retrieval Method=RL-Index2026.06 | 59.1 | 55.4 | 62 | 60.7 | 61 | 42.7 | 55.5 | 56.6 | |
| SBERTGenerator=Llama, Retrieval Method=SBERT2026.06 | 56.5 | 53.3 | 58 | 61.8 | 63.4 | 44.5 | 53.1 | 55.8 |