GAVEL - Explanation Score: leaderboard
Metric: LLM score (0-100; GPT-5 rates each explanation against the annotated one on a 0-5 scale, x20, averaged over all test sentences). Source: arxiv.org. Saturation forecast: Around January 2027. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 | 70 |
| 2 | GPT-5 Mini | 70 |
| 3 | Qwen 3 VL 30B A3B Instruct | 62 |
| 4 | Qwen 3 VL 8B Instruct | 54 |
Interactive version: theaggregate.ai/benchmark?slug=gavel-explanation-score · How It Works · Data refreshed daily, snapshot 2026-09-26.