SEAL - Professional Reasoning Benchmark - Finance: leaderboard
600 expert-created finance questions covering risk assessment, financial analysis, and regulatory reasoning, evaluated by domain professionals using rubrics with 10-30 weighted criteria.
Metric: Score. Source: scale.com. Saturation forecast: Around 2030. 38 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Muse Spark 1.3 | 59.54 | #24 |
| 2 | Muse Wonder | 58.67 | #15 |
| 3 | Muse Spark 1.1 | 55.01 | #52 |
| 4 | Claude Fable 5 | 53.86 | #16 |
| 5 | Claude Opus 4.6 (Non-reasoning) | 53.28 | #63 (Claude Opus 4.6) |
| 6 | Muse Spark | 52.44 | #64 |
| 7 | GPT-5 | 51.32 | #98 |
| 8 | GPT-5 Pro | 51.06 | #81 |
| 9 | Claude Fable 5.1 | 50.8 | #9 |
| 10 | GPT-5.6 Sol (Max) | 50.45 | #19 (GPT-5.6 Sol) |
| 11 | Gemini 4 Argon | 49.9 | #8 |
| 12 | Gemini 3.8 Flash | 49.51 | #21 |
| 13 | O3 Pro | 49.08 | #116 |
| 14 | GPT-5.1 (Thinking) | 48.01 | #135 (GPT-5.1) |
| 15 | O3 | 47.69 | #124 |
No result here: #3 Claude Opus 5.5, #10 Muse Wonder Full.
Interactive version: theaggregate.ai/benchmark?slug=seal-professional-reasoning-benchmark-finance · How It Works · Data refreshed daily, snapshot 2026-10-20.