PulseAugur
EN
LIVE 00:22:01
한국어(KO) Artificial Analysis가 Harvey의 Legal Agent Benchmark(LAB)를 Stirrup 에이전트로 구현한 Harvey LAB‑AA 결과를 공개했습니다. Harvey 데이터셋(120개 비공개 과제, 24개 법률 분야)으로 기준별 합격률과 전항목(all-pass

Kimi K3 leads Harvey Legal Agent Benchmark with 94.6% pass rate

By PulseAugur Editorial · [1 sources] ·

Artificial Analysis has released the results of their Harvey LAB-AA benchmark, which implements Harvey's Legal Agent Benchmark (LAB) using the Stirrup agent. The evaluation used the Harvey dataset, comprising 120 private tasks across 24 legal domains, to assess pass rates by criteria and overall. Kimi K3 achieved the highest score at 94.6%, followed by Claude Fable 5 at 93.6% and Muse Spark 1.1 at 93.1%. The results also include metrics for cost, tokens, and speed. AI

IMPACT Sets a new benchmark for AI agents in legal tasks, highlighting Kimi K3's leading performance and providing comparative data for other models.

RANK_REASON The cluster reports on the results of a benchmark evaluation of AI agents on legal tasks. [lever_c_demoted from research: ic=1 ai=1.0]

Read on Mastodon — fosstodon.org →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

Kimi K3 leads Harvey Legal Agent Benchmark with 94.6% pass rate

COVERAGE [1]

  1. Mastodon — fosstodon.org TIER_1 한국어(KO) · [email protected] ·

    Artificial Analysis has released the results of Harvey LAB-AA, an implementation of Harvey's Legal Agent Benchmark (LAB) as a Stirrup agent. The Harvey dataset (120 private tasks, 24 legal domains) shows the per-benchmark pass rate and all-pass rate.

    Artificial Analysis가 Harvey의 Legal Agent Benchmark(LAB)를 Stirrup 에이전트로 구현한 Harvey LAB‑AA 결과를 공개했습니다. Harvey 데이터셋(120개 비공개 과제, 24개 법률 분야)으로 기준별 합격률과 전항목(all-pass) 합격률을 평가했으며, Kimi K3가 94.6%로 1위, Claude Fable 5 93.6%, Muse Spark 1.1 93.1%로 뒤를 이었습니다. 비용·토큰·속도 지표도 함께 제시됩니다. https:// …

    LINKS artificialanalysis.ai/…/harvey-lab-aa

RELATED ENTITIES

RELATED TOPICS