# Professional work benchmarks

> Source: Benchize (https://benchize.com) — https://benchize.com/benchmarks/category/professional. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/benchmarks/category/professional.

Explore Professional work 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/professional
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.

Evaluate legal, financial, healthcare, and other specialist work. Check each task's domain, required expertise, and scoring method when interpreting model performance.

Published Oct 21, 2026

## [HLAB-Vals-1.1 / criteria pass rate immigration](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acriteria_pass_rate__immigration.md)

Updated: 10/21/2026

Models tested: 14

Tests an agent's ability to complete legal work using documents, spreadsheets, presentations, and file-system tools

Top models · Vals AI

Latest result per model · 1.1

- 1[Muse Wonder](https://benchize.com/models/muse-wonder-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 →

## [HLAB-Vals-1.1 / criteria pass rate insurance](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acriteria_pass_rate__insurance.md)

Updated: 10/21/2026

Models tested: 14

Tests an agent's ability to complete legal work using documents, spreadsheets, presentations, and file-system tools

Top models · Vals AI

Latest result per model · 1.1

- 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 →

## [HLAB-Vals-1.1 / criteria pass rate intellectual property](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acriteria_pass_rate__intellectual_property.md)

Updated: 10/21/2026

Models tested: 14

Tests an agent's ability to complete legal work using documents, spreadsheets, presentations, and file-system tools

Top models · Vals AI

Latest result per model · 1.1

- 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 Sonnet 5.5](https://benchize.com/models/claude-sonnet-5-5-max.md)Max

View details →

## [HLAB-Vals-1.1 / criteria pass rate international trade sanctions](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acriteria_pass_rate__international_trade_sanctions.md)

Updated: 10/21/2026

Models tested: 14

Tests an agent's ability to complete legal work using documents, spreadsheets, presentations, and file-system tools

Top models · Vals AI

Latest result per model · 1.1

- 1[Muse Wonder](https://benchize.com/models/muse-wonder-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 →

## [HLAB-Vals-1.1 / criteria pass rate litigation dispute resolution](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acriteria_pass_rate__litigation_dispute_resolution.md)

Updated: 10/21/2026

Models tested: 14

Tests an agent's ability to complete legal work using documents, spreadsheets, presentations, and file-system tools

Top models · Vals AI

Latest result per model · 1.1

- 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[Gemini 3.8 Flash](https://benchize.com/models/gemini-3-8-flash-high.md)High

View details →

## [HLAB-Vals-1.1 / criteria pass rate real estate](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acriteria_pass_rate__real_estate.md)

Updated: 10/21/2026

Models tested: 14

Tests an agent's ability to complete legal work using documents, spreadsheets, presentations, and file-system tools

Top models · Vals AI

Latest result per model · 1.1

- 1[Muse Wonder](https://benchize.com/models/muse-wonder-max.md)Max

- 2[Gemini 4 Argon](https://benchize.com/models/gemini-4-argon-high.md)High

- 3[GPT-6.1 Sol](https://benchize.com/models/gpt-6-1-sol-max.md)Max

View details →

## [HLAB-Vals-1.1 / criteria pass rate structured finance securitization](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acriteria_pass_rate__structured_finance_securitization.md)

Updated: 10/21/2026

Models tested: 14

Tests an agent's ability to complete legal work using documents, spreadsheets, presentations, and file-system tools

Top models · Vals AI

Latest result per model · 1.1

- 1[Muse Wonder](https://benchize.com/models/muse-wonder-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 →

## [HLAB-Vals-1.1 / criteria pass rate tax](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acriteria_pass_rate__tax.md)

Updated: 10/21/2026

Models tested: 14

Tests an agent's ability to complete legal work using documents, spreadsheets, presentations, and file-system tools

Top models · Vals AI

Latest result per model · 1.1

- 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[MiMo-V2.6-Pro](https://benchize.com/models/mimo-v2-6-pro.md)

View details →

## [HLAB-Vals-1.1 / criteria pass rate trusts estates private client](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acriteria_pass_rate__trusts_estates_private_client.md)

Updated: 10/21/2026

Models tested: 14

Tests an agent's ability to complete legal work using documents, spreadsheets, presentations, and file-system tools

Top models · Vals AI

Latest result per model · 1.1

- 1[Muse Wonder](https://benchize.com/models/muse-wonder-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 →

## [HLAB-Vals-1.1 / criteria pass rate white collar defense investigations](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acriteria_pass_rate__white_collar_defense_investigations.md)

Updated: 10/21/2026

Models tested: 14

Tests an agent's ability to complete legal work using documents, spreadsheets, presentations, and file-system tools

Top models · Vals AI

Latest result per model · 1.1

- 1[Muse Wonder](https://benchize.com/models/muse-wonder-max.md)Max

- 2[Gemini 4 Argon](https://benchize.com/models/gemini-4-argon-high.md)High

- 3[Gemini 3.8 Flash](https://benchize.com/models/gemini-3-8-flash-high.md)High

View details →

## [HLAB-Vals-1.1 / data privacy cybersecurity](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Adata_privacy_cybersecurity.md)

Updated: 10/21/2026

Models tested: 14

Tests an agent's ability to complete legal work using documents, spreadsheets, presentations, and file-system tools

Top models · Vals AI

Latest result per model · 1.1

- 1[Gemini 4 Argon](https://benchize.com/models/gemini-4-argon-high.md)High

- 2[MiMo-V2.6-Pro](https://benchize.com/models/mimo-v2-6-pro.md)

- 3[Claude Opus 5.5](https://benchize.com/models/claude-opus-5-5-max.md)Max

View details →

## [HLAB-Vals-1.1 / emerging companies venture capital](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Aemerging_companies_venture_capital.md)

Updated: 10/21/2026

Models tested: 14

Tests an agent's ability to complete legal work using documents, spreadsheets, presentations, and file-system tools

Top models · Vals AI

Latest result per model · 1.1

- 1[Muse Wonder](https://benchize.com/models/muse-wonder-max.md)Max

- 2[Gemini 3.8 Flash](https://benchize.com/models/gemini-3-8-flash-high.md)High

- 3[GPT-6 Astra](https://benchize.com/models/gpt-6-astra-max.md)Max

View details →

## [HLAB-Vals-1.1 / employment labor](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Aemployment_labor.md)

Updated: 10/21/2026

Models tested: 14

Tests an agent's ability to complete legal work using documents, spreadsheets, presentations, and file-system tools

Top models · Vals AI

Latest result per model · 1.1

- 1[Muse Wonder](https://benchize.com/models/muse-wonder-max.md)Max

- 2[Claude Sonnet 5.5](https://benchize.com/models/claude-sonnet-5-5-max.md)Max

- 3[Gemini 3.8 Flash](https://benchize.com/models/gemini-3-8-flash-high.md)High

View details →

## [HLAB-Vals-1.1 / energy natural resources](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Aenergy_natural_resources.md)

Updated: 10/21/2026

Models tested: 14

Tests an agent's ability to complete legal work using documents, spreadsheets, presentations, and file-system tools

Top models · Vals AI

Latest result per model · 1.1

- 1[Muse Wonder](https://benchize.com/models/muse-wonder-max.md)Max

- 2[Claude Opus 5.5](https://benchize.com/models/claude-opus-5-5-max.md)Max

- 3[DeepSeek V4 Pro 0813](https://benchize.com/models/deepseek-v4-pro-0813-max.md)Max

View details →

## [HLAB-Vals-1.1 / environmental esg](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Aenvironmental_esg.md)

Updated: 10/21/2026

Models tested: 14

Tests an agent's ability to complete legal work using documents, spreadsheets, presentations, and file-system tools

Top models · Vals AI

Latest result per model · 1.1

- 1[Muse Wonder](https://benchize.com/models/muse-wonder-max.md)Max

- 2[Gemini 4 Argon](https://benchize.com/models/gemini-4-argon-high.md)High

- 3[GPT-6.1 Sol](https://benchize.com/models/gpt-6-1-sol-max.md)Max

View details →

## [HLAB-Vals-1.1 / funds asset management](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Afunds_asset_management.md)

Updated: 10/21/2026

Models tested: 14

Tests an agent's ability to complete legal work using documents, spreadsheets, presentations, and file-system tools

Top models · Vals AI

Latest result per model · 1.1

- 1[Gemini 4 Argon](https://benchize.com/models/gemini-4-argon-high.md)High

- 2[DeepSeek V4.1 Flash 1017](https://benchize.com/models/deepseek-v4-1-flash-1017-max.md)Max

- 3[MiMo-V2.6-Flash](https://benchize.com/models/mimo-v2-6-flash.md)

View details →

## [HLAB-Vals-1.1 / healthcare life sciences](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Ahealthcare_life_sciences.md)

Updated: 10/21/2026

Models tested: 14

Tests an agent's ability to complete legal work using documents, spreadsheets, presentations, and file-system tools

Top models · Vals AI

Latest result per model · 1.1

- 1[Gemini 4 Argon](https://benchize.com/models/gemini-4-argon-high.md)High

- 2[MiMo-V2.6-Pro](https://benchize.com/models/mimo-v2-6-pro.md)

- 3[DeepSeek V4.1 Flash 1017](https://benchize.com/models/deepseek-v4-1-flash-1017-max.md)Max

View details →

## [HLAB-Vals-1.1 / immigration](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Aimmigration.md)

Updated: 10/21/2026

Models tested: 14

Tests an agent's ability to complete legal work using documents, spreadsheets, presentations, and file-system tools

Top models · Vals AI

Latest result per model · 1.1

- 1[Muse Wonder](https://benchize.com/models/muse-wonder-max.md)Max

- 2[DeepSeek V4 Pro 0813](https://benchize.com/models/deepseek-v4-pro-0813-max.md)Max

- 3[Claude Sonnet 5.5](https://benchize.com/models/claude-sonnet-5-5-max.md)Max

View details →

## [HLAB-Vals-1.1 / insurance](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Ainsurance.md)

Updated: 10/21/2026

Models tested: 14

Tests an agent's ability to complete legal work using documents, spreadsheets, presentations, and file-system tools

Top models · Vals AI

Latest result per model · 1.1

- 1[Muse Wonder](https://benchize.com/models/muse-wonder-max.md)Max

- 2[Gemini 4 Argon](https://benchize.com/models/gemini-4-argon-high.md)High

- 3[GPT-6 Astra](https://benchize.com/models/gpt-6-astra-max.md)Max

View details →

## [HLAB-Vals-1.1 / intellectual property](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Aintellectual_property.md)

Updated: 10/21/2026

Models tested: 14

Tests an agent's ability to complete legal work using documents, spreadsheets, presentations, and file-system tools

Top models · Vals AI

Latest result per model · 1.1

- 1[Gemini 4 Argon](https://benchize.com/models/gemini-4-argon-high.md)High

- 2[Claude Sonnet 5.5](https://benchize.com/models/claude-sonnet-5-5-max.md)Max

- 3[Gemini 3.8 Flash](https://benchize.com/models/gemini-3-8-flash-high.md)High

View details →

## [HLAB-Vals-1.1 / international trade sanctions](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Ainternational_trade_sanctions.md)

Updated: 10/21/2026

Models tested: 14

Tests an agent's ability to complete legal work using documents, spreadsheets, presentations, and file-system tools

Top models · Vals AI

Latest result per model · 1.1

- 1[Muse Wonder](https://benchize.com/models/muse-wonder-max.md)Max

- 2[Gemini 3.8 Flash](https://benchize.com/models/gemini-3-8-flash-high.md)High

- 3[Gemini 4 Argon](https://benchize.com/models/gemini-4-argon-high.md)High

View details →

## [HLAB-Vals-1.1 / litigation dispute resolution](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Alitigation_dispute_resolution.md)

Updated: 10/21/2026

Models tested: 14

Tests an agent's ability to complete legal work using documents, spreadsheets, presentations, and file-system tools

Top models · Vals AI

Latest result per model · 1.1

- 1[DeepSeek V4.1 Flash 1017](https://benchize.com/models/deepseek-v4-1-flash-1017-max.md)Max

- 2[DeepSeek V4 Pro 0813](https://benchize.com/models/deepseek-v4-pro-0813-max.md)Max

- 3[MiMo-V2.6-Flash](https://benchize.com/models/mimo-v2-6-flash.md)

View details →

## [HLAB-Vals-1.1 / overall](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Aoverall.md)

Updated: 10/21/2026

Models tested: 14

Tests an agent's ability to complete legal work using documents, spreadsheets, presentations, and file-system tools

Top models · Vals AI

Latest result per model · 1.1

- 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 →

## [HLAB-Vals-1.1 / real estate](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Areal_estate.md)

Updated: 10/21/2026

Models tested: 14

Tests an agent's ability to complete legal work using documents, spreadsheets, presentations, and file-system tools

Top models · Vals AI

Latest result per model · 1.1

- 1[GPT-6.1 Sol](https://benchize.com/models/gpt-6-1-sol-max.md)Max

- 2[Muse Wonder](https://benchize.com/models/muse-wonder-max.md)Max

- 3[Claude Haiku 5.5](https://benchize.com/models/claude-haiku-5-5-max.md)Max

View details →

## [HLAB-Vals-1.1 / structured finance securitization](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Astructured_finance_securitization.md)

Updated: 10/21/2026

Models tested: 14

Tests an agent's ability to complete legal work using documents, spreadsheets, presentations, and file-system tools

Top models · Vals AI

Latest result per model · 1.1

- 1[Gemini 4 Argon](https://benchize.com/models/gemini-4-argon-high.md)High

- 2[Claude Sonnet 5.5](https://benchize.com/models/claude-sonnet-5-5-max.md)Max

- 3[DeepSeek V4.1 Flash 1017](https://benchize.com/models/deepseek-v4-1-flash-1017-max.md)Max

View details →

## [HLAB-Vals-1.1 / tax](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Atax.md)

Updated: 10/21/2026

Models tested: 14

Tests an agent's ability to complete legal work using documents, spreadsheets, presentations, and file-system tools

Top models · Vals AI

Latest result per model · 1.1

- 1[Gemini 4 Argon](https://benchize.com/models/gemini-4-argon-high.md)High

- 2[MiMo-V2.6-Flash](https://benchize.com/models/mimo-v2-6-flash.md)

- 3[Gemini 3.8 Flash](https://benchize.com/models/gemini-3-8-flash-high.md)High

View details →

## [HLAB-Vals-1.1 / trusts estates private client](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Atrusts_estates_private_client.md)

Updated: 10/21/2026

Models tested: 14

Tests an agent's ability to complete legal work using documents, spreadsheets, presentations, and file-system tools

Top models · Vals AI

Latest result per model · 1.1

- 1[Gemini 4 Argon](https://benchize.com/models/gemini-4-argon-high.md)High

- 2[Gemini 3.8 Flash](https://benchize.com/models/gemini-3-8-flash-high.md)High

- 3[MiMo-V2.6-Pro](https://benchize.com/models/mimo-v2-6-pro.md)

View details →

## [HLAB-Vals-1.1 / white collar defense investigations](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Awhite_collar_defense_investigations.md)

Updated: 10/21/2026

Models tested: 14

Tests an agent's ability to complete legal work using documents, spreadsheets, presentations, and file-system tools

Top models · Vals AI

Latest result per model · 1.1

- 1[Muse Wonder](https://benchize.com/models/muse-wonder-max.md)Max

- 2[GPT-6.1 Sol](https://benchize.com/models/gpt-6-1-sol-max.md)Max

- 3[Gemini 3.8 Flash](https://benchize.com/models/gemini-3-8-flash-high.md)High

View details →

## [LegalBench / conclusion tasks](https://benchize.com/benchmarks/vals-ai%3Alegal_bench%3Aconclusion_tasks.md)

Updated: 10/21/2026

Models tested: 44

Evaluating language models on a wide range of open source legal reasoning tasks.

Top models · Vals AI

Latest result per model · 1

- 1[Claude Fable 5.1](https://benchize.com/models/claude-fable-5-1-max.md)Max

- 2[Claude Fable 5](https://benchize.com/models/claude-fable-5-max.md)Max

- 3[Claude Opus 5](https://benchize.com/models/claude-opus-5-max.md)Max

View details →

## [LegalBench / interpretation tasks](https://benchize.com/benchmarks/vals-ai%3Alegal_bench%3Ainterpretation_tasks.md)

Updated: 10/21/2026

Models tested: 44

Evaluating language models on a wide range of open source legal reasoning tasks.

Top models · Vals AI

Latest result per model · 1

- 1[Gemini 3.5 Flash](https://benchize.com/models/gemini-3-5-flash-high.md)High

- 2[Claude Fable 5.1](https://benchize.com/models/claude-fable-5-1-max.md)Max

- 3[Claude Fable 5](https://benchize.com/models/claude-fable-5-max.md)Max

View details →

## [LegalBench / issue tasks](https://benchize.com/benchmarks/vals-ai%3Alegal_bench%3Aissue_tasks.md)

Updated: 10/21/2026

Models tested: 44

Evaluating language models on a wide range of open source legal reasoning tasks.

Top models · Vals AI

Latest result per model · 1

- 1[Gemini 4 Argon](https://benchize.com/models/gemini-4-argon-high.md)High

- 2[Claude Fable 5.1](https://benchize.com/models/claude-fable-5-1-max.md)Max

- 3[Gemini 3.7 Flash](https://benchize.com/models/gemini-3-7-flash-high.md)High

View details →

## [LegalBench / overall](https://benchize.com/benchmarks/vals-ai%3Alegal_bench%3Aoverall.md)

Updated: 10/21/2026

Models tested: 44

Evaluating language models on a wide range of open source legal reasoning tasks.

Top models · Vals AI

Latest result per model · 1

- 1[Claude Fable 5](https://benchize.com/models/claude-fable-5-max.md)Max

- 2[Claude Fable 5.1](https://benchize.com/models/claude-fable-5-1-max.md)Max

- 3[Gemini 4 Argon](https://benchize.com/models/gemini-4-argon-high.md)High

View details →

## [LegalBench / rhetoric tasks](https://benchize.com/benchmarks/vals-ai%3Alegal_bench%3Arhetoric_tasks.md)

Updated: 10/21/2026

Models tested: 44

Evaluating language models on a wide range of open source legal reasoning tasks.

Top models · Vals AI

Latest result per model · 1

- 1[Gemini 3.1 Pro Preview](https://benchize.com/models/gemini-3-1-pro-preview-high.md)High

- 2[Gemini 3 Flash Preview](https://benchize.com/models/gemini-3-flash-preview-high.md)High

- 3[Claude Fable 5](https://benchize.com/models/claude-fable-5-max.md)Max

View details →

## [LegalBench / rule tasks](https://benchize.com/benchmarks/vals-ai%3Alegal_bench%3Arule_tasks.md)

Updated: 10/21/2026

Models tested: 44

Evaluating language models on a wide range of open source legal reasoning tasks.

Top models · Vals AI

Latest result per model · 1

- 1[Gemini 4 Argon](https://benchize.com/models/gemini-4-argon-high.md)High

- 2[Claude Fable 5](https://benchize.com/models/claude-fable-5-max.md)Max

- 3[Gemini 3.1 Pro Preview](https://benchize.com/models/gemini-3-1-pro-preview-high.md)High

View details →

## [PRBench Legal](https://benchize.com/benchmarks/scale%3Aprbench-legal.md)

Updated: 10/21/2026

Models tested: 26

Realistic legal reasoning tasks graded against detailed expert-written criteria for professional work.

Top models · scale

Latest result per model · Version not reported

- 1[Muse Spark 1.3](https://benchize.com/models/muse-spark-1-3.md)

- 2[Muse Spark Open](https://benchize.com/models/muse-spark-open.md)

- 3[Muse Spark 1.1](https://benchize.com/models/muse-spark-1-1.md)

View details →

## [TaxEval v2 / correctness](https://benchize.com/benchmarks/vals-ai%3Atax_eval_v2%3Acorrectness.md)

Updated: 10/21/2026

Models tested: 40

A Vals-created set of questions and responses to tax questions

Top models · Vals AI

Latest result per model · 2

- 1[Muse Spark 1.2](https://benchize.com/models/muse-spark-1-2-xhigh.md)Extra high

- 2[Muse Spark 1.1](https://benchize.com/models/muse-spark-1-1-xhigh.md)Extra high

- 3[GPT-5.6 Luna](https://benchize.com/models/gpt-5-6-luna-max.md)Max

View details →

## [TaxEval v2 / overall](https://benchize.com/benchmarks/vals-ai%3Atax_eval_v2%3Aoverall.md)

Updated: 10/21/2026

Models tested: 40

A Vals-created set of questions and responses to tax questions

Top models · Vals AI

Latest result per model · 2

- 1[Muse Spark 1.2](https://benchize.com/models/muse-spark-1-2-xhigh.md)Extra high

- 2[Muse Spark 1.1](https://benchize.com/models/muse-spark-1-1-xhigh.md)Extra high

- 3[Claude Sonnet 4.6](https://benchize.com/models/claude-sonnet-4-6-max.md)Max

View details →

## [TaxEval v2 / stepwise reasoning](https://benchize.com/benchmarks/vals-ai%3Atax_eval_v2%3Astepwise_reasoning.md)

Updated: 10/21/2026

Models tested: 40

A Vals-created set of questions and responses to tax questions

Top models · Vals AI

Latest result per model · 2

- 1[Muse Spark 1.2](https://benchize.com/models/muse-spark-1-2-xhigh.md)Extra high

- 2[Muse Spark 1.1](https://benchize.com/models/muse-spark-1-1-xhigh.md)Extra high

- 3[Claude Sonnet 4.6](https://benchize.com/models/claude-sonnet-4-6-max.md)Max

View details →

## [CorpFin v2 / exact pages](https://benchize.com/benchmarks/vals-ai%3Acorp_fin_v2%3Aexact_pages.md)

Updated: 10/21/2026

Models tested: 39

A private benchmark evaluating understanding of long-context credit agreements

Top models · Vals AI

Latest result per model · 2

- 1[Claude Opus 5](https://benchize.com/models/claude-opus-5.md)

- 2[Gemini 3 Flash Preview](https://benchize.com/models/gemini-3-flash-preview-high.md)High

- 3[Claude Fable 5](https://benchize.com/models/claude-fable-5-max.md)Max

View details →

## [CorpFin v2 / max fitting context](https://benchize.com/benchmarks/vals-ai%3Acorp_fin_v2%3Amax_fitting_context.md)

Updated: 10/21/2026

Models tested: 39

A private benchmark evaluating understanding of long-context credit agreements

Top models · Vals AI

Latest result per model · 2

- 1[Claude Fable 5](https://benchize.com/models/claude-fable-5-max.md)Max

- 2[Claude Opus 5](https://benchize.com/models/claude-opus-5.md)

- 3[Muse Spark 1.1](https://benchize.com/models/muse-spark-1-1-xhigh.md)Extra high

View details →

## [CorpFin v2 / overall](https://benchize.com/benchmarks/vals-ai%3Acorp_fin_v2%3Aoverall.md)

Updated: 10/21/2026

Models tested: 39

A private benchmark evaluating understanding of long-context credit agreements

Top models · Vals AI

Latest result per model · 2

- 1[Claude Opus 5](https://benchize.com/models/claude-opus-5.md)

- 2[Claude Fable 5](https://benchize.com/models/claude-fable-5-max.md)Max

- 3[Muse Spark 1.1](https://benchize.com/models/muse-spark-1-1-xhigh.md)Extra high

View details →

## [CorpFin v2 / shared max context](https://benchize.com/benchmarks/vals-ai%3Acorp_fin_v2%3Ashared_max_context.md)

Updated: 10/21/2026

Models tested: 39

A private benchmark evaluating understanding of long-context credit agreements

Top models · Vals AI

Latest result per model · 2

- 1[Claude Opus 5](https://benchize.com/models/claude-opus-5.md)

- 2[Muse Spark 1.1](https://benchize.com/models/muse-spark-1-1-xhigh.md)Extra high

- 3[Muse Spark 1.2](https://benchize.com/models/muse-spark-1-2-xhigh.md)Extra high

View details →

## [MortgageTax / numerical extraction](https://benchize.com/benchmarks/vals-ai%3Amortgage_tax%3Anumerical_extraction.md)

Updated: 10/21/2026

Models tested: 31

Evaluating reading and understanding tax certificates as images

Top models · Vals AI

Latest result per model · 1

- 1[Claude Opus 5](https://benchize.com/models/claude-opus-5.md)

- 2[Claude Opus 4.8](https://benchize.com/models/claude-opus-4-8-max.md)Max

- 3[Claude Opus 4.7](https://benchize.com/models/claude-opus-4-7-max.md)Max

View details →

## [MortgageTax / overall](https://benchize.com/benchmarks/vals-ai%3Amortgage_tax%3Aoverall.md)

Updated: 10/21/2026

Models tested: 31

Evaluating reading and understanding tax certificates as images

Top models · Vals AI

Latest result per model · 1

- 1[Claude Opus 5](https://benchize.com/models/claude-opus-5.md)

- 2[Claude Fable 5.1](https://benchize.com/models/claude-fable-5-1-max.md)Max

- 3[Claude Opus 4.7](https://benchize.com/models/claude-opus-4-7-max.md)Max

View details →

## [MortgageTax / semantic extraction](https://benchize.com/benchmarks/vals-ai%3Amortgage_tax%3Asemantic_extraction.md)

Updated: 10/21/2026

Models tested: 31

Evaluating reading and understanding tax certificates as images

Top models · Vals AI

Latest result per model · 1

- 1[Claude Fable 5.1](https://benchize.com/models/claude-fable-5-1-max.md)Max

- 2[Claude Opus 5](https://benchize.com/models/claude-opus-5.md)

- 3[Gemini 3.1 Pro Preview](https://benchize.com/models/gemini-3-1-pro-preview-high.md)High

View details →

## [ClaimBench / direct support](https://benchize.com/benchmarks/vals-ai%3Aclaimbench%3Adirect_support.md)

Conquered

Updated: 10/21/2026

Models tested: 5

Does a 10-K excerpt support a claim, contradict it, or say nothing about it?

Top models · Vals AI

Latest result per model · 1

- 1[Claude Sonnet 5.5](https://benchize.com/models/claude-sonnet-5-5-max.md)Max

- 2[GPT-6 Luna](https://benchize.com/models/gpt-6-luna-max.md)Max

- 3[Claude Haiku 5.5](https://benchize.com/models/claude-haiku-5-5-max.md)Max

View details →

## [ClaimBench / missing evidence](https://benchize.com/benchmarks/vals-ai%3Aclaimbench%3Amissing_evidence.md)

Conquered

Updated: 10/21/2026

Models tested: 5

Does a 10-K excerpt support a claim, contradict it, or say nothing about it?

Top models · Vals AI

Latest result per model · 1

- 1[Claude Haiku 5.5](https://benchize.com/models/claude-haiku-5-5-max.md)Max

- 2[GPT-6 Luna](https://benchize.com/models/gpt-6-luna-max.md)Max

- 3[Claude Opus 5.5](https://benchize.com/models/claude-opus-5-5-max.md)Max

View details →

## [ClaimBench / non supporting citation](https://benchize.com/benchmarks/vals-ai%3Aclaimbench%3Anon_supporting_citation.md)

Conquered

Updated: 10/21/2026

Models tested: 5

Does a 10-K excerpt support a claim, contradict it, or say nothing about it?

Top models · Vals AI

Latest result per model · 1

- 1[Claude Opus 5.5](https://benchize.com/models/claude-opus-5-5-max.md)Max

- 2[GPT-6.1 Sol](https://benchize.com/models/gpt-6-1-sol-max.md)Max

- 3[GPT-6 Luna](https://benchize.com/models/gpt-6-luna-max.md)Max

View details →

## [ClaimBench / numeric discrepancy](https://benchize.com/benchmarks/vals-ai%3Aclaimbench%3Anumeric_discrepancy.md)

Conquered

Updated: 10/21/2026

Models tested: 5

Does a 10-K excerpt support a claim, contradict it, or say nothing about it?

Top models · Vals AI

Latest result per model · 1

- 1[GPT-6.1 Sol](https://benchize.com/models/gpt-6-1-sol-max.md)Max

- 2[GPT-6 Luna](https://benchize.com/models/gpt-6-luna-max.md)Max

- 3[Claude Opus 5.5](https://benchize.com/models/claude-opus-5-5-max.md)Max

View details →

## [ClaimBench / overall](https://benchize.com/benchmarks/vals-ai%3Aclaimbench%3Aoverall.md)

Conquered

Updated: 10/21/2026

Models tested: 5

Does a 10-K excerpt support a claim, contradict it, or say nothing about it?

Top models · Vals AI

Latest result per model · 1

- 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-6.1 Sol](https://benchize.com/models/gpt-6-1-sol-max.md)Max

View details →

## [ClaimBench / subtle contradiction](https://benchize.com/benchmarks/vals-ai%3Aclaimbench%3Asubtle_contradiction.md)

Conquered

Updated: 10/21/2026

Models tested: 5

Does a 10-K excerpt support a claim, contradict it, or say nothing about it?

Top models · Vals AI

Latest result per model · 1

- 1[Claude Haiku 5.5](https://benchize.com/models/claude-haiku-5-5-max.md)Max

- 2[Claude Sonnet 5.5](https://benchize.com/models/claude-sonnet-5-5-max.md)Max

- 3[Claude Opus 5.5](https://benchize.com/models/claude-opus-5-5-max.md)Max

View details →

## [PRBench Finance](https://benchize.com/benchmarks/scale%3Aprbench-finance.md)

Updated: 10/21/2026

Models tested: 22

Realistic financial reasoning and decision tasks graded against detailed expert-written criteria.

Top models · scale

Latest result per model · Version not reported

- 1[Muse Spark 1.3](https://benchize.com/models/muse-spark-1-3.md)

- 2[Muse Spark 1.1](https://benchize.com/models/muse-spark-1-1.md)

- 3[Claude Fable 5](https://benchize.com/models/claude-fable-5.md)

View details →

## [Public Benefits Bench v1 / both](https://benchize.com/benchmarks/vals-ai%3Apublic-benefits-bench-v1%3Aboth.md)

Updated: 10/21/2026

Models tested: 8

Can AI help people navigate SNAP benefits?

Top models · Vals AI

Latest result per model · 1

- 1[Claude Fable 5](https://benchize.com/models/claude-fable-5-max.md)Max

- 2[Claude Opus 4.8](https://benchize.com/models/claude-opus-4-8-max.md)Max

- 3[MiniMax M3](https://benchize.com/models/minimax-m3.md)

View details →

## [Public Benefits Bench v1 / multi turn](https://benchize.com/benchmarks/vals-ai%3Apublic-benefits-bench-v1%3Amulti_turn.md)

Updated: 10/21/2026

Models tested: 8

Can AI help people navigate SNAP benefits?

Top models · Vals AI

Latest result per model · 1

- 1[Claude Fable 5](https://benchize.com/models/claude-fable-5-max.md)Max

- 2[Claude Opus 4.8](https://benchize.com/models/claude-opus-4-8-max.md)Max

- 3[Gemini 3.5 Flash](https://benchize.com/models/gemini-3-5-flash-high.md)High

View details →

## [Public Benefits Bench v1 / neither](https://benchize.com/benchmarks/vals-ai%3Apublic-benefits-bench-v1%3Aneither.md)

Updated: 10/21/2026

Models tested: 8

Can AI help people navigate SNAP benefits?

Top models · Vals AI

Latest result per model · 1

- 1[Claude Fable 5](https://benchize.com/models/claude-fable-5-max.md)Max

- 2[Claude Opus 4.8](https://benchize.com/models/claude-opus-4-8-max.md)Max

- 3[Gemini 3.5 Flash](https://benchize.com/models/gemini-3-5-flash-high.md)High

View details →

## [Public Benefits Bench v1 / overall](https://benchize.com/benchmarks/vals-ai%3Apublic-benefits-bench-v1%3Aoverall.md)

Updated: 10/21/2026

Models tested: 8

Can AI help people navigate SNAP benefits?

Top models · Vals AI

Latest result per model · 1

- 1[Claude Fable 5](https://benchize.com/models/claude-fable-5-max.md)Max

- 2[Claude Opus 4.8](https://benchize.com/models/claude-opus-4-8-max.md)Max

- 3[MiniMax M3](https://benchize.com/models/minimax-m3.md)

View details →

## [Public Benefits Bench v1 / web search](https://benchize.com/benchmarks/vals-ai%3Apublic-benefits-bench-v1%3Aweb_search.md)

Updated: 10/21/2026

Models tested: 8

Can AI help people navigate SNAP benefits?

Top models · Vals AI

Latest result per model · 1

- 1[Claude Fable 5](https://benchize.com/models/claude-fable-5-max.md)Max

- 2[Claude Opus 4.8](https://benchize.com/models/claude-opus-4-8-max.md)Max

- 3[Gemini 3.5 Flash](https://benchize.com/models/gemini-3-5-flash-high.md)High

View details →

## [CaseLaw v2 / overall](https://benchize.com/benchmarks/vals-ai%3Acase_law_v2%3Aoverall.md)

Updated: 10/21/2026

Models tested: 17

Private question-answer benchmark over Canadian court-cases.

Top models · Vals AI

Latest result per model · 2

- 1[Claude Opus 4.7](https://benchize.com/models/claude-opus-4-7.md)

- 2[GPT-5.5](https://benchize.com/models/gpt-5-5-xhigh.md)Extra high

- 3[Gemini 3.1 Pro Preview](https://benchize.com/models/gemini-3-1-pro-preview-high.md)High

View details →

## [MedQA / asian](https://benchize.com/benchmarks/vals-ai%3Amedqa%3Aasian.md)

Updated: 10/21/2026

Models tested: 12

Evaluating language model bias in medical questions.

Top models · Vals AI

Latest result per model · 1

- 1[Gemini 3.1 Pro Preview](https://benchize.com/models/gemini-3-1-pro-preview-high.md)High

- 2[Gemini 3 Flash Preview](https://benchize.com/models/gemini-3-flash-preview-high.md)High

- 3[MiniMax M2.5](https://benchize.com/models/minimax-m2-5.md)

View details →

## [MedQA / black](https://benchize.com/benchmarks/vals-ai%3Amedqa%3Ablack.md)

Updated: 10/21/2026

Models tested: 12

Evaluating language model bias in medical questions.

Top models · Vals AI

Latest result per model · 1

- 1[Gemini 3.1 Pro Preview](https://benchize.com/models/gemini-3-1-pro-preview-high.md)High

- 2[Gemini 3 Flash Preview](https://benchize.com/models/gemini-3-flash-preview-high.md)High

- 3[Claude Sonnet 4.6](https://benchize.com/models/claude-sonnet-4-6-thinking.md)Thinking

View details →

## [MedQA / hispanic](https://benchize.com/benchmarks/vals-ai%3Amedqa%3Ahispanic.md)

Updated: 10/21/2026

Models tested: 12

Evaluating language model bias in medical questions.

Top models · Vals AI

Latest result per model · 1

- 1[Gemini 3.1 Pro Preview](https://benchize.com/models/gemini-3-1-pro-preview-high.md)High

- 2[Gemini 3 Flash Preview](https://benchize.com/models/gemini-3-flash-preview-high.md)High

- 3[MiniMax M2.5](https://benchize.com/models/minimax-m2-5.md)

View details →

## [MedQA / indigenous](https://benchize.com/benchmarks/vals-ai%3Amedqa%3Aindigenous.md)

Updated: 10/21/2026

Models tested: 12

Evaluating language model bias in medical questions.

Top models · Vals AI

Latest result per model · 1

- 1[Gemini 3.1 Pro Preview](https://benchize.com/models/gemini-3-1-pro-preview-high.md)High

- 2[Gemini 3 Flash Preview](https://benchize.com/models/gemini-3-flash-preview-high.md)High

- 3[MiniMax M2.5](https://benchize.com/models/minimax-m2-5.md)

View details →

## [MedQA / overall](https://benchize.com/benchmarks/vals-ai%3Amedqa%3Aoverall.md)

Updated: 10/21/2026

Models tested: 12

Evaluating language model bias in medical questions.

Top models · Vals AI

Latest result per model · 1

- 1[Gemini 3.1 Pro Preview](https://benchize.com/models/gemini-3-1-pro-preview-high.md)High

- 2[Gemini 3 Flash Preview](https://benchize.com/models/gemini-3-flash-preview-high.md)High

- 3[MiniMax M2.5](https://benchize.com/models/minimax-m2-5.md)

View details →

## [MedQA / unbiased](https://benchize.com/benchmarks/vals-ai%3Amedqa%3Aunbiased.md)

Updated: 10/21/2026

Models tested: 12

Evaluating language model bias in medical questions.

Top models · Vals AI

Latest result per model · 1

- 1[Gemini 3.1 Pro Preview](https://benchize.com/models/gemini-3-1-pro-preview-high.md)High

- 2[Gemini 3 Flash Preview](https://benchize.com/models/gemini-3-flash-preview-high.md)High

- 3[MiniMax M2.5](https://benchize.com/models/minimax-m2-5.md)

View details →

## [MedQA / white](https://benchize.com/benchmarks/vals-ai%3Amedqa%3Awhite.md)

Updated: 10/21/2026

Models tested: 12

Evaluating language model bias in medical questions.

Top models · Vals AI

Latest result per model · 1

- 1[Gemini 3 Flash Preview](https://benchize.com/models/gemini-3-flash-preview-high.md)High

- 2[Gemini 3.1 Pro Preview](https://benchize.com/models/gemini-3-1-pro-preview-high.md)High

- 3[MiniMax M2.5](https://benchize.com/models/minimax-m2-5.md)

View details →

## [TutorBench](https://benchize.com/benchmarks/scale%3Atutorbench.md)

Updated: 10/21/2026

Models tested: 5

Large Language Models serve as on-demand tutors for learners worldwide, yet, a critical evaluation gap exists. While most benchmarks assess an LLM's ability to solve problems,…

Top models · scale

Latest result per model · Version not reported

- 1[Gemini 2.5 Pro Preview 06-05](https://benchize.com/models/gemini-2-5-pro-preview.md)

- 2[Claude Opus 4.6](https://benchize.com/models/claude-opus-4-6-off.md)Non-thinking

- 3[Gemini 3.1 Pro Preview](https://benchize.com/models/gemini-3-1-pro-preview.md)

View details →

## [Arena text / industry business and management and financial operations](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_business_and_management_and_financial_operations.md)

Updated: 10/21/2026

Models tested: 151

Human pairwise preferences on industry business and management and financial operations prompts in Arena’s text evaluation. The original organizer publishes model ratings and…

Top models · Arena

Latest result per model · Version not reported

- 1[Gemini 4 Argon](https://benchize.com/models/gemini-4-argon-high.md)High

- 2[Claude Opus 5](https://benchize.com/models/claude-opus-5-max.md)Max

- 3[Claude Opus 4.6](https://benchize.com/models/claude-opus-4-6-high.md)High

View details →

## [Arena text / industry legal and government](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_legal_and_government.md)

Updated: 10/21/2026

Models tested: 151

Human pairwise preferences on industry legal and government prompts in Arena’s text evaluation. The original organizer publishes model ratings and uncertainty; these are…

Top models · Arena

Latest result per model · Version not reported

- 1[Gemini 4 Argon](https://benchize.com/models/gemini-4-argon-high.md)High

- 2[Claude Opus 5](https://benchize.com/models/claude-opus-5-max.md)Max

- 3[Claude Opus 5](https://benchize.com/models/claude-opus-5-high.md)High

View details →

## [Arena text / industry medicine and healthcare](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_medicine_and_healthcare.md)

Updated: 10/21/2026

Models tested: 151

Human pairwise preferences on industry medicine and healthcare prompts in Arena’s text evaluation. The original organizer publishes model ratings and uncertainty; these are…

Top models · Arena

Latest result per model · Version not reported

- 1[Gemini 4 Argon](https://benchize.com/models/gemini-4-argon-high.md)High

- 2[Claude Fable 5.1](https://benchize.com/models/claude-fable-5-1-max.md)Max

- 3[Claude Opus 5](https://benchize.com/models/claude-opus-5-max.md)Max

View details →

## [Arena text style control / industry business and management and financial operations](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_business_and_management_and_financial_operations.md)

Updated: 10/21/2026

Models tested: 151

Human pairwise preferences on industry business and management and financial operations prompts in Arena’s text style control evaluation. The original organizer publishes model…

Top models · Arena

Latest result per model · Version not reported

- 1[Gemini 4 Argon](https://benchize.com/models/gemini-4-argon-high.md)High

- 2[Claude Opus 4.7](https://benchize.com/models/claude-opus-4-7-high.md)High

- 3[Muse Spark 1.2](https://benchize.com/models/muse-spark-1-2-xhigh.md)Extra high

View details →

## [Arena text style control / industry legal and government](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_legal_and_government.md)

Updated: 10/21/2026

Models tested: 151

Human pairwise preferences on industry legal and government prompts in Arena’s text style control evaluation. The original organizer publishes model ratings and uncertainty,…

Top models · Arena

Latest result per model · Version not reported

- 1[Gemini 4 Argon](https://benchize.com/models/gemini-4-argon-high.md)High

- 2[Muse Spark 1.2](https://benchize.com/models/muse-spark-1-2-xhigh.md)Extra high

- 3[Claude Fable 5](https://benchize.com/models/claude-fable-5-high.md)High

View details →

## [Arena text style control / industry medicine and healthcare](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_medicine_and_healthcare.md)

Updated: 10/21/2026

Models tested: 151

Human pairwise preferences on industry medicine and healthcare prompts in Arena’s text style control evaluation. The original organizer publishes model ratings and uncertainty,…

Top models · Arena

Latest result per model · Version not reported

- 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 Fable 5.1](https://benchize.com/models/claude-fable-5-1-max.md)Max

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: Professional work benchmarks — Benchize, https://benchize.com/benchmarks/category/professional (retrieved 2026-10-21)