Enter opens the highlighted result. Esc closes.

Legal Research Bench leaderboard

As of November 14, 2026, among the results listed here, Thinking Machines Inkling 2 Small has the highest reported Legal Research Bench score, 46.6%, published by Thinking Machines, ahead of MoonshotAI Kimi K3 at 44.2%. 2 models have a Legal Research Bench result in our records.

Scores as the model makers published them, not re-run by us; each row links to its announcement.

Best reported score

46.6%

T Thinking Machines Inkling 2 Small

Reported by Thinking Machines, November 9, 2026

Runner-up

44.2%

MoonshotAI Kimi K3

Reported by Moonshot AI, July 16, 2026 · max

2 models ranked · 2 makers

Reported Legal Research Bench scores

Legal Research Bench scores reported by model makers
Rank Model Score Setting Reported by Date
1 T Inkling 2 Small 46.6% Not published Thinking Machines November 9, 2026 (model release)
2 Kimi K3 44.2% max Moonshot AI July 16, 2026 (model release)

How much to trust these numbers

Source
Reported by the model makers themselves. Not re-run by LLMBenchmark or anyone independent.
Settings
Settings differ between makers. Check the Setting column before comparing two scores.
Spread
46.6% to 44.2% across 2 models.
Freshness
Newest result published November 9, 2026; oldest July 16, 2026.

What Legal Research Bench measures

Models answer expert-written, open-ended U.S. legal research questions, and the score reflects how often answers pass all requirements across 208 private test questions. Source: Legal Research Bench