LLM-as-a-Judge on JudgeBench (Merged GPT Claude)
87.38Direct Baseline Scoreqwen3.5-35b
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| qwen3.5-35bScale=1–10, Count=6202026.04 | 87.38 | 83.65 | 85.47 | 87.19 | 87.19 | |
| qwen3.5-35bScale=1–5, Count=6202026.04 | 85.73 | 83.6 | 86.24 | 86.95 | 86.69 | |
| qwen3.5-9bScale=1–10, Count=6202026.04 | 82.7 | 81.44 | 83.55 | 84.07 | 84.03 | |
| qwen3.5-9bScale=1–5, Count=6202026.04 | 81.91 | 82.4 | 83.87 | 84.66 | 84.21 | |
| gpt-oss-120bScale=1–10, Count=6202026.04 | 75.81 | 80.49 | 80.97 | 82.1 | 82.1 | |
| gpt-oss-120bScale=1–5, Count=6202026.04 | 75 | 78.06 | 78.23 | 78.87 | 78.71 | |
| gpt-oss-20bScale=1–5, Count=6202026.04 | 71.77 | 75.48 | 76.45 | 78.06 | 78.55 | |
| gpt-oss-20bScale=1–10, Count=6202026.04 | 69.83 | 74.52 | 75.35 | 76.95 | 77.6 |