The AI arena is free today

Open Superagent

Vals Index

Implementation

Progress Over Time

Interactive timeline showing model performance evolution on Vals Index

State-of-the-art frontier
Open
Proprietary

Vals Index Leaderboard

2 models
ContextCostLicense
1—1.0M$2.00 / $10.00
2—1.0M$2.00 / $10.00
Notice missing or incorrect data?
About this benchmark

What is Vals Index?

Vals Index measures economic impact across finance, coding, legal, and tax work, with every sector weighted by its contribution to U.S. GDP.

Vals Index is a text benchmark evaluating models on knowledge, reasoning, and agents tasks. LLM Stats tracks 2 models on this benchmark, scored on a 0–1 scale. The current average is 0.7, with the leader at 0.7.

Compare leaders on the best AI for knowledge, best AI for reasoning and best AI for agents leaderboards.

Current leaders

Gemini 4 Carbon from Google currently leads the Vals Index leaderboard with a score of 0.704 across 2 evaluated AI models.

1Gemini 4 CarbonGoogle70.4%
2Gemini 4 ArgonGoogle68.9%

FAQ

Common questions about the Vals Index benchmark and leaderboard.

What is the Vals Index benchmark?

Vals Index measures economic impact across finance, coding, legal, and tax work, with every sector weighted by its contribution to U.S. GDP.

What is the Vals Index leaderboard?

The Vals Index leaderboard ranks 2 AI models based on their performance on this benchmark. Currently, Gemini 4 Carbon by Google leads with a score of 0.704. The average score across all models is 0.696.

What is the highest Vals Index score?

The highest Vals Index score is 0.704, achieved by Gemini 4 Carbon from Google.

How many models are evaluated on Vals Index?

2 models have been evaluated on the Vals Index benchmark, with 0 verified results and 2 self-reported results.

Where can I find the Vals Index dataset?

The Vals Index dataset is available at https://www.vals.ai/.

What categories does Vals Index cover?

Vals Index is categorized under knowledge, reasoning, and agents. The benchmark evaluates text models.

Which model offers the best value on Vals Index?

Among models scoring within 10% of the leader, Gemini 4 Carbon from Google is the cheapest, at $2.00 per million input tokens with a score of 0.704.

How recent are the Vals Index leaderboard results?

The Vals Index leaderboard was last updated in November 2026 and currently includes 2 evaluated models.