PulseAugur
EN
LIVE 14:03:31
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

How we ranked this

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
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]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
product, paper
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
49 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

Full methodology in our editorial standards.

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