Vals AI Finance Agent: leaderboard
Agentic SEC filing research tasks for financial analysts: quantitative retrieval, GAAP adjustments, earnings analysis, trend identification, and multi-document modeling.
Metric: Accuracy (%). Source: www.vals.ai. Source: benchmarklist.com. Saturation forecast: Around January 2027. 51 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.7 (High) | 64.37 | #49 (Claude Opus 4.7) |
| 2 | Claude Sonnet 4.6 (Max) | 63.33 | #90 (Claude Sonnet 4.6) |
| 3 | GPT-5.4 Pro (xHigh) | 61.5 | #32 (GPT-5.4 Pro) |
| 4 | Muse Spark | 60.59 | #64 |
| 5 | DeepSeek V4 Pro (Max) | 60.39 | #102 (DeepSeek V4 Pro) |
| 6 | Claude Opus 4.6 | 60.1 | #63 |
| 7 | Claude Opus 4.6 (Adaptive Reasoning, Max Effort) | 60.05 | #63 (Claude Opus 4.6) |
| 8 | GPT-5.5 (xHigh) | 59.96 | #31 (GPT-5.5) |
| 9 | Gemini 3.1 Pro (Preview) (High) | 59.72 | #58 (Gemini 3.1 Pro (Preview)) |
| 10 | Claude Opus 4.5 (20251101) (Thinking, High) | 58.81 | #74 (Claude Opus 4.5 (20251101)) |
| 11 | GPT-5.2 (2025-12-11) (xHigh) | 58.53 | |
| 12 | GLM-5.1 | 57.66 | #97 |
| 13 | GPT-5.4 (2026-03-05) (xHigh) | 57.15 | #59 (GPT-5.4 (2026-03-05)) |
| 14 | Kimi K2.6 | 57.06 | #104 |
| 15 | GPT-5.1 (2025-11-13) (High) | 55.31 | #101 (GPT-5.1 (2025-11-13)) |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=vals-ai-finance-agent · How It Works · Data refreshed daily, snapshot 2026-10-20.