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 verifiedBenchmark 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.
Benchmark score table (1 model)
ScoreAbout 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
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.