Vals Index — leaderboard
Benchmark consisting of a weighted performance across finance and coding tasks. Showing the potential impact that LLM's can have on the economy.
Metric: Score (self-reported). Source: benchmarklist.com. Status: saturation imminent. 25 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Fable 5 (Max) | 75.14 |
| 2 | Claude Opus 4.8 (Max) | 70.36 |
| 3 | GPT-5.5 (xHigh) | 67.95 |
| 4 | Claude Opus 4.7 (High) | 66.1 |
| 5 | Gemini 3.5 Flash (High) | 62.75 |
| 6 | Claude Sonnet 4.6 (Max) | 60.06 |
| 7 | MiniMax-M3 | 58.94 |
| 8 | Qwen 3.7 Max (Max) | 57.49 |
| 9 | DeepSeek V4 Pro (Max) | 55.62 |
| 10 | Gemini 3.1 Pro (Preview) (High) | 53.77 |
| 11 | GLM-5.1 | 52.45 |
| 12 | GPT-5.4 Mini (xHigh) | 52.42 |
| 13 | Qwen 3.7 Plus | 52.33 |
| 14 | Gemini 3 Flash (Preview) (High) | 49.55 |
| 15 | Qwen 3.6 Plus | 48.89 |
Interactive version: theaggregate.ai/benchmark?slug=vals-index · How the rankings work · Data refreshed daily, snapshot 2026-07-22.