Completeness on ASQA
0.54Kendall's TauJury-on-Demand
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Jury-on-Demand2025.12 | 0.54 | 0.05 | |
| Claude 3.7Judge Model=Claude 3.72025.12 | 0.42 | 0.03 | |
| Gemini 2.0 FlashJudge Model=Gemini 2.0 Flash2025.12 | 0.38 | 0.04 | |
| GPT-OSS-120BJudge Model=GPT-OSS-120B2025.12 | 0.38 | 0.05 | |
| Gemma 3Judge Model=Gemma 32025.12 | 0.36 | 0.05 | |
| Gemini 2.5 ProJudge Model=Gemini 2.5 Pro2025.12 | 0.34 | 0.05 | |
| Gemini 2.5 FlashJudge Model=Gemini 2.5 Flash2025.12 | 0.33 | 0.05 | |
| GPT-OSS-20BJudge Model=GPT-OSS-20B2025.12 | 0.33 | 0.04 | |
| LLAMA 3.2Judge Model=LL-3.22025.12 | 0.22 | 0.05 | |
| DeepSeek R1Judge Model=DeepSeek R12025.12 | 0.2 | 0.06 | |
| Phi 4Judge Model=Phi 42025.12 | 0.13 | 0.04 |