SEAL - Professional Reasoning Benchmark - Legal: leaderboard
Metric: Score. Source: scale.com. 32 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Muse Spark 1.1 | 57.05 |
| 2 | Claude Fable 5 | 52.56 |
| 3 | Muse Spark | 52.29 |
| 4 | Claude Opus 4.6 (Non-reasoning) | 52.27 |
| 5 | Claude Fable 5.1 (xHigh) | 51.6 |
| 6 | GPT-5.6 Sol (Max) | 50.5 |
| 7 | GPT-5 Pro | 49.89 |
| 8 | O3 Pro | 49.67 |
| 9 | GPT-5.1 (Thinking) | 49.33 |
| 10 | GPT-5 | 48.96 |
| 11 | O3 | 48.57 |
| 12 | GPT-5.2 Pro | 45.44 |
| 13 | GPT-5.4 (High) | 44.35 |
| 14 | Claude Opus 4.5 (20251101) (Thinking) | 44.21 |
| 15 | Gemini 3.1 Pro (Preview) | 44.02 |
Interactive version: theaggregate.ai/benchmark?slug=seal-professional-reasoning-benchmark-legal · How It Works · Data refreshed daily, snapshot 2026-09-05.