Kimi K3 Leads Legal Benchmark
petrusenko_max · x · 2026-07-19
Kimi K3 scored 26.7% on a challenging autonomous legal work benchmark, nearly doubling the score of its recent competitor Claude Fable 5 (14.2%).
The test covers 24 legal areas with 120 private tasks, including memos and deposition summaries. Models are required to fully process case files and output final documents under strict grading: missing any single rubric detail results in a failure. The author points out that while 27% is a leading score, there is still a long way to go before AI can reliably and independently handle legal work.
Related event: Kimi K3 Leads Harvey Legal Benchmark(4 posts)→
More from Models
- MissionReport benchmark: only 3 of 540 AI-generated government reports pass all criteria — Exp_Mark · 2026-10-27
- Local beats cloud: Qwen 3.8 FN handles private student data as well as frontier models — dr_lm · 2026-10-27
- Aidan Gomez: model's CoT said no tool calls right before making them — aidangomez · 2026-10-27
- Nat Lambert: Cohere's model is narrow RL training on internal infra ill-suited for open weights — natolambert · 2026-10-27
- OpenAI teases DOTS is coming to Europe 'soon' — mark_k · 2026-10-27
- Clifford Pickover challenges AI to decipher a message he encoded in Norse runes — pickover · 2026-10-27