Skip to main content

Benchmark profile

Legal Agent Benchmark mean criterion-pass rate — Anthropic harness (LAB criterion-pass (Anthropic harness))

Mean fraction of expert-written rubric criteria passed across legal-agent tasks.

Data verified

Benchmark score on LAB criterion-pass (Anthropic harness) — July 24, 2026

BenchLM mirrors the published score view for LAB criterion-pass (Anthropic harness). Claude Opus 5 leads the public snapshot at 93.74%. BenchLM does not use these results to rank models overall.

1 modelAgenticCurrentDisplay onlyUpdated July 24, 2026

Benchmark score table (1 model)

Score
1
Claude Opus 5Anthropic · Closed
93.74%

About LAB criterion-pass (Anthropic harness)

Year

2026

Tasks

1,235 legal-agent tasks

Format

Mean criterion-pass rate

Difficulty

Professional legal work

Section 8.13.3 reports this auxiliary criterion-level metric from Anthropic's reduced-tool reimplementation.

BenchLM freshness & provenance

Version

LAB criterion-pass (Anthropic harness) 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.

FAQ

What does LAB criterion-pass (Anthropic harness) measure?

Mean fraction of expert-written rubric criteria passed across legal-agent tasks.

Which model scores highest on LAB criterion-pass (Anthropic harness)?

Claude Opus 5 by Anthropic currently leads with a score of 93.74% on LAB criterion-pass (Anthropic harness).

How many models are evaluated on LAB criterion-pass (Anthropic harness)?

1 AI models have been evaluated on LAB criterion-pass (Anthropic harness) on BenchLM.

Last updated: July 24, 2026 · BenchLM version LAB criterion-pass (Anthropic harness) 2026