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

#ModelScore
1Claude Fable 5 (Max)75.14
2Claude Opus 574.82
3Kimi K374.7
4GPT-5.6 Sol (Max)73.12
5Claude Opus 4.8 (Max)70.36
6GPT-5.6 Luna (Max)69.88
7Claude Sonnet 5 (Max)68.61
8Muse Spark 1.1 (xHigh)68.41
9GPT-5.5 (xHigh)67.95
10Claude Opus 4.7 (High)66.1
11Grok 4.5 (High)65.3
12GPT-5.6 Terra (xHigh)65.14
13GLM-5.2 (Max)65.02
14Gemini 3.5 Flash (High)62.75
15Gemini 3.6 Flash (High)62.43

Interactive version: theaggregate.ai/benchmark?slug=vals-index · How It Works · Data refreshed daily, snapshot 2026-09-05.