The Chat Judge verdicts

Which AI is best at what?

Public benchmark results for 19 tests across 9 fields, charted side by side. Every score links to the leaderboard it came from.

Showing MiniMax's best-ranked model on each benchmark.

1 benchmarkUpdated 19 Oct 2026Overall workOne number for agentic work across finance, coding, law and tax.

Vals Index MiniMax-M3.1-Flash #15 · 53.78%

See charts 3 benchmarksUpdated 19 Oct 2026LegalDrafting, extraction, legal reasoning and US legal research.

Legal Benchmarks leaderboard MiniMax M3 #6 · 80.0%
LegalBench MiniMax-M3 #21 · 85.42%

See charts 2 benchmarksUpdated 19 Oct 2026FinanceAnalyst research on SEC filings and long credit agreements.

Finance Agent MiniMax-M3.1-Flash #22 · 58.83%
CorpFin v2 MiniMax-M3 #11 · 68.10%

See charts 2 benchmarksUpdated 19 Oct 2026Agents & tool useMulti-step tasks an agent completes alone in a terminal.

Terminal-Bench 4.0 MiniMax-M3.1-Flash #22 · 25.25%

See charts 4 benchmarksUpdated 21 Oct 2026Reasoning & knowledgeExpert exams, graduate science, contest maths and broad knowledge.

GPQA Diamond MiniMax-M3 #15 · 92.68%

See charts

ChatJudge does not run these tests. Scores are copied as published by each source, with a link and the date we read them, and only change when we refresh from the source. Different leaderboards use different settings, so compare models within one chart, not across charts. Spotted a mistake? Tell us.