Benchmark · KnowledgeSettled

Professional Reasoning · Legal

Updated 2026-04-07
Models tested
6
Top score
52.3
Claude Opus 4.6 (Fast)
Median
49.8
min 48.6
Top-5 spread
σ 1.4
Settled

Best score over time · one chart, every benchmark

PROFESSIONAL REASONING · LEGAL6 MODELS · FRONTIER RUNNING MAX0255075100SCORE ↑Apr 25Jul 25Oct 25Jan 26Apr 26RELEASE DATE →benchgecko.ai/benchmark/seal-pro-reasoning-legal · frontier
Frontier on Professional Reasoning · Legal rose from 48.6 to 52.3 in 10 months · +3.7 points · latest leader Claude Opus 4.6 from Anthropic.
Pink dots = frontier records · 4 totalClick to open model page

6 models tested · sorted by score

#ModelScore
1Anthropic logoClaude Opus 4.6 (Fast)52.3
2Anthropic logoClaude Opus 4.652.3
3OpenAI logoGPT-5 Pro49.9
4OpenAI logoo3 Pro49.7
5OpenAI logoGPT-549.0
6OpenAI logoo348.6

What it measures · how it is scored · sources · as of 2026-11-17

  • What it measures · SEAL Pro Reasoning Legal. Tests legal reasoning and case analysis ability.
  • How it is scored · Scored as a percentage · higher is better · maximum 100
  • Scores from · Scale SEAL leaderboards (6 scores)

Same category · related evaluations