Skip to content
aiqbench

Alibaba · model passport

Qwen3 Max

qwen3-max
  • Cloud only
  • Proprietary licence
  • Released 2025-09-05(curated)
11/27axes covered
Overall · LMArena
1,423#114 of 396
Best percentile
87.3MMLU-Pro (Artificial Analysis)
Cohort standing
65.8median 51.9

What the data says

Benchmarked on 11 of 27 tracked axes. Every figure below is the model's own published result on that board.

Strongest axes

  • 87.3 pct — MMLU-Pro (Artificial Analysis) (84.1%)
  • 85.9 pct — LiveCodeBench (Artificial Analysis) (76.7%)

Uneven: 33.5 percentile points between its best and worst axis — 87.3 pct on MMLU-Pro (Artificial Analysis) versus 53.8 pct on GPQA Diamond.

  • MMLU-Pro (Artificial Analysis)87.3 pct84.1%Verify →
  • LiveCodeBench (Artificial Analysis)85.9 pct76.7%Verify →
  • LiveBench81.8 pct69.9%Verify →
  • Hard prompts72.7 pct1,446Verify →
  • Coding72.6 pct1,473Verify →
  • Overall71.5 pct1,423Verify →
  • Instruction following71.5 pct1,414Verify →
  • SimpleQA Verified64.6 pct48.7%Verify →
  • AIME (math)54.5 pct73.3%Verify →
  • IFBench (Artificial Analysis)54.3 pct48.0%Verify →
  • GPQA Diamond53.8 pct72.6%Verify →
  • WebDev ArenaNot benchmarked
  • Vision ArenaNot benchmarked
  • Factuality ArenaNot benchmarked
  • Search ArenaNot benchmarked
  • Document ArenaNot benchmarked
  • Agent ArenaNot benchmarked
  • FrontierMathNot benchmarked
  • ARC-AGI-2Not benchmarked
  • Humanity's Last ExamNot benchmarked
  • SimpleBenchNot benchmarked
  • BFCL v4 (function calling)Not benchmarked
  • SWE-bench Verified (live board)Not benchmarked
  • Terminal-Bench 4.0Not benchmarked
  • HHEM Hallucination (Vectara)Not benchmarked
  • SWE-bench VerifiedNot benchmarked
  • Terminal-BenchNot benchmarked

Percentiles are the model's standing within each board's own population. Axes marked "not benchmarked" have no published result for this model — that is an absence of data, not a low score.

  • qwen3-max-2025-09-23 stands at 65.8 (raw mean 70) — measured on 11 of 27 axes.

    standingtemplateVerify →

  • qwen3-max-2025-09-23 stands at 65.8 versus a cohort median of 51.9 across 146 models released within 180 days — above the peer median.

    cohorttemplateVerify →

Every claim is a computed fact from the current board data, phrased by a low-temperature model call and rejected by a validation gate if any number is not in the source row. How the leaderboards work →