Which model leads Legal Agent Benchmark (LAB) mean criterion-pass rate?

Claude Fable 5.1 leads the Legal Agent Benchmark (LAB) mean criterion-pass rate board of 2 measured models on the Vector Wire tracker at 90.81. Every score is source-attributed with a verification tier.

Legal Agent Benchmark (LAB) mean criterion-pass rate Leaderboard — Model Scores

Refresh Models —Deals —Regulatory —Sources —

Pro Mode — raw scores, one benchmark under the lensofficial card harness

The field · 2 measured

88.4890.81

2 models measured, most on the official card harness. Claude Fable 5.1 tops the board at 90.81.

2 measured·1 new this week·Lifecycle Updated Sep 1, 2026Basis

#◆Vendor$/M in$/M out

Leader — ignites whiteField — fill cools with scoreIndependently verified only0 of 2Bars show 88.48–90.81· ◆ solid = first-party or better · outlined = arm's-length

01Claude Fable 5.1NEWAnthropic90.81———

02Claude Sonnet 4.6Anthropic88.48$3.0/M$15.0/M$0.102

◆ solid = independently verified · aggregator attested · vendor attributed — outlined = cross-reference · source-attributed. Dimmed ◆ = confidence inferred. “+N alts” = alternate disclosures in the drawer with why-demoted. Prices per million tokens; $/point = input price ÷ score. Every row opens its model dossier.