Vals AI Finance Index: leaderboard
Vals Finance Index v1: native overall aggregate across the released financial evaluations; preserves every published model and explicit reasoning setting.
Metric: Finance Index (%). Source: www.vals.ai. Saturation forecast: Around 2029. 28 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 5.5 (Max) | 65.59 | #4 (Claude Opus 5.5) |
| 2 | Gemini 4 Argon (High) | 64.89 | #8 (Gemini 4 Argon) |
| 3 | Muse Wonder Full (Max) | 64.55 | #10 (Muse Wonder Full) |
| 4 | Claude Sonnet 5.5 (Max) | 64.53 | #11 (Claude Sonnet 5.5) |
| 5 | Muse Wonder (Max) | 61.23 | #14 (Muse Wonder) |
| 6 | DeepSeek V4.1 Flash (1017) (Max) | 60.89 | #21 (DeepSeek V4.1 Flash (1017)) |
| 7 | GLM-5.3 (Max) | 60.54 | #37 (GLM-5.3) |
| 8 | Gemini 3.8 Flash (High) | 60.46 | #24 (Gemini 3.8 Flash) |
| 9 | Grok 4.7 (xHigh) | 58.46 | #27 (Grok 4.7) |
| 10 | Kimi K3 (Max) | 57.96 | #30 (Kimi K3) |
| 11 | MiMo-V2.6-Pro | 57.85 | #38 |
| 12 | Hy4 preview | 57.51 | #39 |
| 13 | Claude Haiku 5.5 (Max) | 57.45 | #40 (Claude Haiku 5.5) |
| 14 | MiMo-V2.6-Flash | 57.15 | #73 |
| 15 | DeepSeek V4.1 Flash (Max) | 57.08 | #35 (DeepSeek V4.1 Flash) |
No result here: #9 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=vals-ai-finance-index · How It Works · Data refreshed daily, snapshot 2026-10-22.