VECTOR WIREAI INTELLIGENCE
⌘K
NVDA$1,847+3.2%MSFT$512+1.1%GOOGL$199-0.4%META$728+2.7%AMD$184-1.2%TSM$212+0.6%PLTR$98+4.1%AI IDX4,821+1.9%
PKT
SEEDRefresh Models —Deals —Regulatory —Sources —

Legal Agent Benchmark (Harvey's Held-Out Set)

4 models tracked

Legal Agent Benchmark, Harvey's Held-Out Set — Distinct, much harder subset (0.8-13.3) than Full Public Set (8-16.9) - correctly separate.

#ModelVendorBest scoreRunsLast seen
1Claude Fable 5Anthropic13.312026-06-10
2Claude Sonnet 4.6Anthropic5.412026-06-30
3GPT-5.5OpenAI2.112026-06-30
4Gemini 3.5 FlashGoogle0.812026-06-30

Best tracked score per model (default configuration; source-attributed and verification-tiered). Open a model for its full benchmark surface, provenance and pricing.