Vals Multimodal Index: leaderboard
Vals AI averages its finance, coding and education benchmark results, weighting each sector by its share of United States output. The parts cover finance and tax documents, software and terminal tasks, and grading handwritten student maths. Vals has archived it and no longer adds new models; it spans 0 to 100, higher is better, read here via benchmarklist.com. Source: vals.ai/benchmarks/vals_multimodal_index.
Metric: Score (imported). Source: benchmarklist.com. Saturation forecast: Around September 2027. 29 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Fable 5 (Max) | 74.15 | #16 (Claude Fable 5) |
| 2 | Claude Opus 5 | 73.9 | #12 |
| 3 | Kimi K3 | 73.42 | #30 |
| 4 | GPT-5.6 Sol (Max) | 72.19 | #19 (GPT-5.6 Sol) |
| 5 | Claude Opus 4.8 (Max) | 70.89 | #37 (Claude Opus 4.8) |
| 6 | GPT-5.6 Luna (Max) | 69.06 | #68 (GPT-5.6 Luna) |
| 7 | Claude Sonnet 5 (Max) | 68.83 | #57 (Claude Sonnet 5) |
| 8 | GPT-5.5 (xHigh) | 68.07 | #31 (GPT-5.5) |
| 9 | Claude Opus 4.7 (High) | 67.36 | #49 (Claude Opus 4.7) |
| 10 | Muse Spark 1.1 (xHigh) | 66.74 | #52 (Muse Spark 1.1) |
| 11 | GPT-5.6 Terra (xHigh) | 65.07 | #41 (GPT-5.6 Terra) |
| 12 | Grok 4.5 (High) | 63.42 | #48 (Grok 4.5) |
| 13 | Gemini 3.5 Flash (High) | 62.93 | #60 (Gemini 3.5 Flash) |
| 14 | Gemini 3.6 Flash (High) | 62.8 | #51 (Gemini 3.6 Flash) |
| 15 | Claude Sonnet 4.6 (Max) | 60.57 | #90 (Claude Sonnet 4.6) |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=vals-multimodal-index · How It Works · Data refreshed daily, snapshot 2026-10-20.