Skip to main content

Vals Harvey's Legal Agent Benchmark (Harvey's Legal Agent Benchmark)

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

Data verified

How BenchLM shows Harvey's Legal Agent Benchmark

BenchLM mirrors the public Vals AI Harvey's Legal Agent Benchmark leaderboard captured from https://www.vals.ai/benchmarks/hlab and updated by Vals on July 9, 2026. The snapshot preserves overall scores, uncertainty, latency, cost-per-test metadata, and task-level scores where Vals publishes them.

Harvey's Legal Agent Benchmark is display only on BenchLM. Vals proprietary or Vals-hosted aggregate views are useful context, but BenchLM does not use them as weighted ranking inputs or as a replacement for benchmark-native source records.

19 Vals rows50 task viewspublic datasetTasks: Overall, Antitrust Competition, Arbitration International Dispute Resolution, Banking Finance, Bankruptcy RestructuringDisplay only

Harvey's Legal Agent Benchmark score on Harvey's Legal Agent Benchmark — July 9, 2026

BenchLM mirrors the published harvey's legal agent benchmark score view for Harvey's Legal Agent Benchmark. Muse Spark 1 1 leads the public snapshot at 20.00% , followed by Grok 4.5 (12.92%) and Claude Fable 5 (11.25%). BenchLM does not use these results to rank models overall.

19 modelsExternal benchmark mirrorsCurrentDisplay onlyUpdated July 9, 2026

The published Harvey's Legal Agent Benchmark snapshot is tightly clustered at the top: Muse Spark 1 1 sits at 20.00%, while the third row is only 8.75 points behind. The broader top-10 spread is 16.25 points, so the benchmark still separates strong models even when the leaders cluster.

19 models have been evaluated on Harvey's Legal Agent Benchmark. The benchmark falls in the External benchmark mirrors category. BenchLM tracks this category separately from its weighted global scoring system, so these results are best compared on the dedicated Korean benchmark views. Harvey's Legal Agent Benchmark is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About Harvey's Legal Agent Benchmark

Year

2026

Tasks

Legal agent work across documents, spreadsheets, presentations, and files

Format

Accuracy score

Difficulty

Professional legal workflow automation

BenchLM mirrors the public Vals AI Harvey's Legal Agent Benchmark leaderboard as display-only external evidence. The captured snapshot preserves overall scores, task-level scores where Vals publishes them, uncertainty, latency, and cost-per-test metadata. It is excluded from BenchLM weighted rankings.

BenchLM freshness & provenance

Version

Harvey's Legal Agent Benchmark 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

CurrentDisplay only

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

Harvey's Legal Agent Benchmark score table (19 models)

1
Muse Spark 1 1meta/muse_spark_1_1
20.00%
2
Grok 4.5grok/grok-4.5
12.92%
3
Claude Fable 5anthropic/claude-fable-5
11.25%
4
Claude Opus 4.8anthropic/claude-opus-4-8
9.58%
5
GLM 5.2zai/glm-5.2
7.08%
6
Claude Sonnet 4.6anthropic/claude-sonnet-4-6
5.00%
7
Claude Sonnet 5anthropic/claude-sonnet-5
5.00%
8
MiniMax M3minimax/MiniMax-M3
4.17%
9
DeepSeek V4 Prodeepseek/deepseek-v4-pro
3.75%
10
GPT-5.5openai/gpt-5.5
3.75%
11
Gemini 3.5 Flashgoogle/gemini-3.5-flash
2.50%
12
GPT-5.6 Solopenai/gpt-5.6-sol
2.50%
13
Kimi K2.6kimi/kimi-k2.6
1.67%
14
Qwen3.7 Maxalibaba/qwen3.7-max
1.67%
15
Grok 4.3grok/grok-4.3
0.42%
16
GPT-5.6 Terraopenai/gpt-5.6-terra
0.42%
17
GLM 5.1zai/glm-5.1
0.00%
18
Qwen3.7 Plusalibaba/qwen3.7-plus
0.00%
19
GPT-5.4openai/gpt-5.4-2026-03-05
0.00%

FAQ

What does Harvey's Legal Agent Benchmark measure?

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

Which model leads the published Harvey's Legal Agent Benchmark snapshot?

Muse Spark 1 1 currently leads the published Harvey's Legal Agent Benchmark snapshot with 20.00% harvey's legal agent benchmark score. BenchLM shows this benchmark for display only and does not use it in overall rankings.

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

19 AI models are included in BenchLM's mirrored Harvey's Legal Agent Benchmark snapshot, based on the public leaderboard captured on July 9, 2026.

Last updated: July 9, 2026 · mirrored from the public benchmark leaderboard

The AI models change fast. We track them for you.

For engineers, researchers, and the plain curious — a weekly brief on new models, ranking shifts, and pricing changes.

Free. No spam. Unsubscribe anytime.