Share promptsSign inCreate team library
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 Alibaba's best-ranked model on each benchmark.

3 benchmarksUpdated 19 Oct 2026LegalDrafting, extraction, legal reasoning and US legal research.
  • Legal Benchmarks leaderboard Qwen 3.8 Flash #15 · 63.5%
  • Legal Research Bench Qwen 3.8 Max #13 · 47.60%
See charts 3 benchmarksUpdated 21 Oct 2026Health & medicalPhysician-graded health conversations, medical coding and exam questions.
  • MedQA Qwen 3.5 Plus #13 · 95.21%
See charts 2 benchmarksUpdated 19 Oct 2026FinanceAnalyst research on SEC filings and long credit agreements.
  • CorpFin v2 Qwen 3 Max Thinking #12 · 68.03%
See charts 2 benchmarksUpdated 1 Sep 2026CodingFixing real GitHub issues and solving fresh programming problems.
  • SWE-bench Verified Qwen 3.8 27B #15 · 86.0%
  • LiveCodeBench Qwen 3.8 Max #10 · 87.85%
See charts 2 benchmarksUpdated 19 Oct 2026Agents & tool useMulti-step tasks an agent completes alone in a terminal.
  • Terminal-Bench 4.0 Qwen 3.8 Max #16 · 34.34%
See charts 4 benchmarksUpdated 21 Oct 2026Reasoning & knowledgeExpert exams, graduate science, contest maths and broad knowledge.
  • GPQA Diamond Qwen 3.8 Max #6 · 93.69%
  • AIME Qwen 3.6 Plus #13 · 94.58%
  • MMLU Pro Qwen 3.7 Max #12 · 89.31%
See charts 1 benchmarkUpdated 20 Oct 2026Chat preferenceWhich answers real people prefer in blind side-by-side votes.
  • LMArena Text Arena Qwen3.8-Max #23 · 1483
See charts 1 benchmarkUpdated 9 Jan 2026MultilingualReasoning in languages other than English.
  • MGSM Qwen 3 (235B) #17 · 92.47%
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.