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. 40 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Fable 5 (Max) | 75.14 |
| 2 | Claude Opus 5 | 74.82 |
| 3 | Kimi K3 | 74.7 |
| 4 | GPT-5.6 Sol (Max) | 73.12 |
| 5 | Claude Opus 4.8 (Max) | 70.36 |
| 6 | GPT-5.6 Luna (Max) | 69.88 |
| 7 | Claude Sonnet 5 (Max) | 68.61 |
| 8 | Muse Spark 1.1 (xHigh) | 68.41 |
| 9 | GPT-5.5 (xHigh) | 67.95 |
| 10 | Claude Opus 4.7 (High) | 66.1 |
| 11 | Grok 4.5 (High) | 65.3 |
| 12 | GPT-5.6 Terra (xHigh) | 65.14 |
| 13 | GLM-5.2 (Max) | 65.02 |
| 14 | Gemini 3.5 Flash (High) | 62.75 |
| 15 | Gemini 3.6 Flash (High) | 62.43 |
Interactive version: theaggregate.ai/benchmark?slug=vals-index · How It Works · Data refreshed daily, snapshot 2026-09-05.