Question Answering on ReCoQA (test)
91.01Type 1 F1HIRE-Agent
Evaluation Results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| HIRE-AgentModel=GLM4.5-Air2026.04 | 91.01 | 91.01 | 80.13 | 79.23 | 60.75 | 60.69 | 73.63 | 73.36 | |
| HIRE-AgentModel=Qwen2.5-72B2026.04 | 88.62 | 88.62 | 67.01 | 65.81 | 62.11 | 62.11 | 70.21 | 69.89 | |
| StandardModel=GLM4.5-Air2026.04 | 86.11 | 86.11 | 63.46 | 62.32 | 41.12 | 40.93 | 58.56 | 58.17 | |
| HIRE-AgentModel=Average2026.04 | 84.53 | 84.53 | 77.68 | 76.58 | 65.4 | 65.35 | 73.52 | 73.23 | |
| HIRE-AgentModel=Qwen3-8B2026.04 | 81.88 | 81.88 | 75.7 | 74.84 | 54.89 | 54.89 | 67.3 | 67.07 | |
| StandardModel=Qwen2.5-72B2026.04 | 80.82 | 80.82 | 72.29 | 71.1 | 40.11 | 39.73 | 59.05 | 58.55 | |
| StandardModel=Average2026.04 | 77.41 | 77.41 | 61.74 | 60.9 | 35.76 | 35.59 | 53.31 | 52.99 | |
| HIRE-AgentModel=Qwen3-30B A3B2026.04 | 76.59 | 76.59 | 87.48 | 86.45 | 83.84 | 83.71 | 82.94 | 82.6 | |
| StandardModel=Qwen3-30B A3B2026.04 | 73.94 | 73.94 | 59.44 | 58.71 | 35.31 | 35.12 | 51.59 | 51.31 | |
| StandardModel=Qwen3-8B2026.04 | 68.78 | 68.78 | 51.76 | 51.48 | 26.49 | 26.57 | 44.05 | 43.93 |