SEAL - Professional Reasoning Benchmark - Finance — leaderboard
Metric: Score. Source: scale.com. 29 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Muse Spark 1.1 | 55.01 |
| 2 | Claude Opus 4.6 (Non-reasoning) | 53.28 |
| 3 | Muse Spark | 52.44 |
| 4 | GPT-5 | 51.32 |
| 5 | GPT-5 Pro | 51.06 |
| 6 | O3 Pro | 49.08 |
| 7 | GPT-5.1 (Thinking) | 48.01 |
| 8 | O3 | 47.69 |
| 9 | Kimi K2.5 | 46.51 |
| 10 | GPT-5.2 Pro | 46.34 |
| 11 | Claude Opus 4.5 (20251101) (Thinking) | 46.16 |
| 12 | GPT-5.4 (High) | 45.63 |
| 13 | GPT-OSS-120B | 43.8 |
| 14 | Claude Sonnet 4.5 | 43.79 |
| 15 | Kimi K2 (Thinking) | 43.41 |
Interactive version: theaggregate.ai/benchmark?slug=seal-professional-reasoning-benchmark-finance · How the rankings work · Data refreshed daily, snapshot 2026-07-22.