Composite indexes benchmarks
Explore composite indexes that combine results across multiple capabilities. Each publisher chooses its own benchmarks, weights, and scale, so indexes should be read with their methodology.
Published
Updated:
Models tested: 14
A single measure of AI's potential economic impact — agentic model performance across finance, coding, legal, and tax tasks, weighted by each sector's share of U.S. GDP.
Top models · Vals AI
Latest result per model · 2.2
- 1Claude Sonnet 5.5Max87.37%
- 2Claude Opus 5.5Max80.49%
- 3GPT-6 AstraMax78.03%
Updated:
Models tested: 14
A single measure of AI's potential economic impact — agentic model performance across finance, coding, legal, and tax tasks, weighted by each sector's share of U.S. GDP.
Top models · Vals AI
Latest result per model · 2.2
- 1Claude Sonnet 5.5Max75.9%
- 2Claude Opus 5.5Max75.84%
- 3Gemini 4 ArgonHigh74.83%
Updated:
Models tested: 14
A single measure of AI's potential economic impact — agentic model performance across finance, coding, legal, and tax tasks, weighted by each sector's share of U.S. GDP.
Top models · Vals AI
Latest result per model · 2.2
- 1Claude Opus 5.5Max67.85%
- 2Gemini 4 ArgonHigh67.66%
- 3Claude Sonnet 5.5Max67.28%
Updated:
Models tested: 14
A single measure of AI's potential economic impact — agentic model performance across finance, coding, legal, and tax tasks, weighted by each sector's share of U.S. GDP.
Top models · Vals AI
Latest result per model · 2.2
- 1Gemini 4 ArgonHigh27.08%
- 2Muse WonderMax23.75%
- 3DeepSeek V4.1 Flash 1017Max14.17%
Updated:
Models tested: 14
A single measure of AI's potential economic impact — agentic model performance across finance, coding, legal, and tax tasks, weighted by each sector's share of U.S. GDP.
Top models · Vals AI
Latest result per model · 2.2
- 1Gemini 4 ArgonHigh54.81%
- 2Muse WonderMax50.48%
- 3Claude Opus 5.5Max50.48%
Updated:
Models tested: 14
A single measure of AI's potential economic impact — agentic model performance across finance, coding, legal, and tax tasks, weighted by each sector's share of U.S. GDP.
Top models · Vals AI
Latest result per model · 2.2
- 1Claude Sonnet 5.5Max70.85%
- 2Claude Opus 5.5Max70.18%
- 3Gemini 4 ArgonHigh69.24%
Updated:
Models tested: 14
A single measure of AI's potential economic impact — agentic model performance across finance, coding, legal, and tax tasks, weighted by each sector's share of U.S. GDP.
Top models · Vals AI
Latest result per model · 2.2
- 1Claude Opus 5.5Max45.57%
- 2Gemini 4 ArgonHigh44.56%
- 3DeepSeek V4.1 Flash 1017Max44.35%
Updated:
Models tested: 14
A single measure of AI's potential economic impact — agentic model performance across finance, coding, legal, and tax tasks, weighted by each sector's share of U.S. GDP.
Top models · Vals AI
Latest result per model · 2.2
- 1Claude Opus 5.5Max65.15%
- 2Claude Sonnet 5.5Max64.14%
- 3GPT-6 AstraMax59.6%
Updated:
Models tested: 14
A single measure of AI's potential economic impact — agentic model performance across finance, coding, legal, and tax tasks, weighted by each sector's share of U.S. GDP.
Top models · Vals AI
Latest result per model · 2.2
- 1Claude Sonnet 5.5Max92.39%
- 2Gemini 4 ArgonHigh91.91%
- 3Claude Haiku 5.5Max90.44%
Updated:
Models tested: 10
Regularly refreshed reasoning, mathematics, coding, language, instruction-following and data-analysis tasks with objectively graded answers. The original release publishes…
Top models · LiveBench
Latest result per model · Version not reported
- 1GLM-5.298%
- 2DeepSeek V4 Flash98%
- 3GPT-5.598%
Methodology and provenance
Benchize collects and structures public benchmark reports. Scores, costs, timings, ranks and uncertainty remain attributed to their original sources. Different versions, configurations and measurement units are separate results. Missing fields stay unavailable.