The AI arena is free today

Open Superagent

Harvey's Legal Agent Benchmark

Implementation

Progress Over Time

Interactive timeline showing model performance evolution on Harvey's Legal Agent Benchmark

State-of-the-art frontier
Open
Proprietary

Harvey's Legal Agent Benchmark Leaderboard

1 models
ContextCostLicense
11.0M$0.75 / $3.75
Notice missing or incorrect data?
About this benchmark

What is Harvey's Legal Agent Benchmark?

Harvey's Legal Agent Benchmark evaluates AI agents on complex legal workflows and reports the all-pass rate.

Harvey's Legal Agent Benchmark is a text benchmark evaluating models on knowledge, legal, reasoning, and agents tasks. LLM Stats tracks 1 models on this benchmark, scored on a 0–1 scale. The current average is 0.1, with the leader at 0.1.

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

Current leaders

Gemini 3.8 Flash from Google currently leads the Harvey's Legal Agent Benchmark leaderboard with a score of 0.100 across 1 evaluated AI models.

1Gemini 3.8 FlashGoogle10.0%

FAQ

Common questions about the Harvey's Legal Agent Benchmark benchmark and leaderboard.

What is the Harvey's Legal Agent Benchmark benchmark?

Harvey's Legal Agent Benchmark evaluates AI agents on complex legal workflows and reports the all-pass rate.

What is the Harvey's Legal Agent Benchmark leaderboard?

The Harvey's Legal Agent Benchmark leaderboard ranks 1 AI models based on their performance on this benchmark. Currently, Gemini 3.8 Flash by Google leads with a score of 0.100. The average score across all models is 0.100.

What is the highest Harvey's Legal Agent Benchmark score?

The highest Harvey's Legal Agent Benchmark score is 0.100, achieved by Gemini 3.8 Flash from Google.

How many models are evaluated on Harvey's Legal Agent Benchmark?

1 models have been evaluated on the Harvey's Legal Agent Benchmark benchmark, with 0 verified results and 1 self-reported results.

Where can I find the Harvey's Legal Agent Benchmark dataset?

The Harvey's Legal Agent Benchmark dataset is available at https://www.vals.ai/.

What categories does Harvey's Legal Agent Benchmark cover?

Harvey's Legal Agent Benchmark is categorized under knowledge, legal, reasoning, and agents. The benchmark evaluates text models.

Which model offers the best value on Harvey's Legal Agent Benchmark?

Among models scoring within 10% of the leader, Gemini 3.8 Flash from Google is the cheapest, at $0.75 per million input tokens with a score of 0.100.

How recent are the Harvey's Legal Agent Benchmark leaderboard results?

The Harvey's Legal Agent Benchmark leaderboard was last updated in September 2026 and currently includes 1 evaluated models.