RuleWeaver - Same-Source - Rubric Score: leaderboard
Metric: Judge rubric score (0-100). Source: arxiv.org. 11 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 (Non-reasoning) | 53.83 |
| 2 | GPT-5.4 (Non-reasoning) | 48.21 |
| 3 | Claude Opus 4.6 (Non-reasoning) | 48.06 |
| 4 | Claude Sonnet 4.6 (Non-reasoning) | 43.96 |
| 5 | GLM-5 (Non-reasoning) | 37.54 |
| 6 | DeepSeek V4 Pro (Non-reasoning) | 34.69 |
| 7 | Kimi K2.6 (Non-reasoning) | 32.5 |
| 8 | Gemini 3.1 Pro (Preview) (Low) | 31.77 |
| 9 | MiniMax-M2.7 | 29.69 |
Interactive version: theaggregate.ai/benchmark?slug=ruleweaver-same-source-rubric-score · How It Works · Data refreshed daily, snapshot 2026-09-19.