# Composite indexes benchmarks > Source: Benchize (https://benchize.com) — https://benchize.com/benchmarks/category/aggregate. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/benchmarks/category/aggregate. Explore Composite indexes LLM benchmarks and AI model results. Compare source-reported scores with original metrics, evaluation settings and evidence on Benchize. Canonical URL: https://benchize.com/benchmarks/category/aggregate Last updated: 2026-10-21T18:52:20.672Z Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations. 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 Oct 21, 2026 ## [Vals Index / code migration](https://benchize.com/benchmarks/vals-ai%3Avals_index%3Acode_migration.md) Updated: 10/21/2026 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 - 1[Claude Sonnet 5.5](https://benchize.com/models/claude-sonnet-5-5-max.md)Max - 2[Claude Opus 5.5](https://benchize.com/models/claude-opus-5-5-max.md)Max - 3[GPT-6 Astra](https://benchize.com/models/gpt-6-astra-max.md)Max View details → ## [Vals Index / emb](https://benchize.com/benchmarks/vals-ai%3Avals_index%3Aemb.md) Updated: 10/21/2026 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 - 1[Claude Sonnet 5.5](https://benchize.com/models/claude-sonnet-5-5-max.md)Max - 2[Claude Opus 5.5](https://benchize.com/models/claude-opus-5-5-max.md)Max - 3[Gemini 4 Argon](https://benchize.com/models/gemini-4-argon-high.md)High View details → ## [Vals Index / finance agent](https://benchize.com/benchmarks/vals-ai%3Avals_index%3Afinance_agent.md) Updated: 10/21/2026 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 - 1[Claude Opus 5.5](https://benchize.com/models/claude-opus-5-5-max.md)Max - 2[Gemini 4 Argon](https://benchize.com/models/gemini-4-argon-high.md)High - 3[Claude Sonnet 5.5](https://benchize.com/models/claude-sonnet-5-5-max.md)Max View details → ## [Vals Index / legal agent benchmark](https://benchize.com/benchmarks/vals-ai%3Avals_index%3Alegal_agent_benchmark.md) Updated: 10/21/2026 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 - 1[Gemini 4 Argon](https://benchize.com/models/gemini-4-argon-high.md)High - 2[Muse Wonder](https://benchize.com/models/muse-wonder-max.md)Max - 3[DeepSeek V4.1 Flash 1017](https://benchize.com/models/deepseek-v4-1-flash-1017-max.md)Max View details → ## [Vals Index / legal research](https://benchize.com/benchmarks/vals-ai%3Avals_index%3Alegal_research.md) Updated: 10/21/2026 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 - 1[Gemini 4 Argon](https://benchize.com/models/gemini-4-argon-high.md)High - 2[Muse Wonder](https://benchize.com/models/muse-wonder-max.md)Max - 3[Claude Opus 5.5](https://benchize.com/models/claude-opus-5-5-max.md)Max View details → ## [Vals Index / overall](https://benchize.com/benchmarks/vals-ai%3Avals_index%3Aoverall.md) Updated: 10/21/2026 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 - 1[Claude Sonnet 5.5](https://benchize.com/models/claude-sonnet-5-5-max.md)Max - 2[Claude Opus 5.5](https://benchize.com/models/claude-opus-5-5-max.md)Max - 3[Gemini 4 Argon](https://benchize.com/models/gemini-4-argon-high.md)High View details → ## [Vals Index / tax agent bench](https://benchize.com/benchmarks/vals-ai%3Avals_index%3Atax_agent_bench.md) Updated: 10/21/2026 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 - 1[Claude Opus 5.5](https://benchize.com/models/claude-opus-5-5-max.md)Max - 2[Gemini 4 Argon](https://benchize.com/models/gemini-4-argon-high.md)High - 3[DeepSeek V4.1 Flash 1017](https://benchize.com/models/deepseek-v4-1-flash-1017-max.md)Max View details → ## [Vals Index / terminal bench 4](https://benchize.com/benchmarks/vals-ai%3Avals_index%3Aterminal_bench_4.md) Updated: 10/21/2026 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 - 1[Claude Opus 5.5](https://benchize.com/models/claude-opus-5-5-max.md)Max - 2[Claude Sonnet 5.5](https://benchize.com/models/claude-sonnet-5-5-max.md)Max - 3[GPT-6 Astra](https://benchize.com/models/gpt-6-astra-max.md)Max View details → ## [Vals Index / vibe code bench](https://benchize.com/benchmarks/vals-ai%3Avals_index%3Avibe_code_bench.md) Updated: 10/21/2026 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 - 1[Claude Sonnet 5.5](https://benchize.com/models/claude-sonnet-5-5-max.md)Max - 2[Gemini 4 Argon](https://benchize.com/models/gemini-4-argon-high.md)High - 3[Claude Haiku 5.5](https://benchize.com/models/claude-haiku-5-5-max.md)Max View details → ## [LiveBench](https://benchize.com/benchmarks/livebench%3Atasks.md) Updated: 10/21/2026 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 - 1[GLM-5.2](https://benchize.com/models/glm-5-2.md) - 2[DeepSeek V4 Flash](https://benchize.com/models/deepseek-v4-flash.md) - 3[GPT-5.5](https://benchize.com/models/gpt-5-5.md) View details → ## 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. --- Cite as: Composite indexes benchmarks — Benchize, https://benchize.com/benchmarks/category/aggregate (retrieved 2026-10-21)