Vals Multimodal Index: leaderboard
Benchmark consisting of a weighted performance across finance, coding, and education tasks. Showing the potential impact that LLM's can have on the economy.
Metric: Accuracy (%). Source: www.vals.ai. Status: saturation imminent. 33 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Fable 5 (Max) | 74.15 |
| 2 | Claude Opus 5 | 73.9 |
| 3 | Kimi K3 | 73.42 |
| 4 | GPT-5.6 Sol (Max) | 72.64 |
| 5 | Claude Opus 4.8 (Max) | 70.89 |
| 6 | Muse Spark 1.2 | 69.8 |
| 7 | GPT-5.6 Luna (Max) | 69.06 |
| 8 | Claude Sonnet 5 (Max) | 68.83 |
| 9 | GPT-5.5 (xHigh) | 68.07 |
| 10 | Claude Opus 4.7 (High) | 67.36 |
| 11 | Muse Spark 1.1 (xHigh) | 66.74 |
| 12 | Qwen 3.8 Max | 65.39 |
| 13 | Gemini 3.6 Flash (High) | 65.08 |
| 14 | GPT-5.6 Terra (xHigh) | 65.07 |
| 15 | Grok 4.5 (High) | 63.42 |
Interactive version: theaggregate.ai/benchmark?slug=vals-multimodal-index · How It Works · Data refreshed daily, snapshot 2026-09-05.