Skip to content
aiqbench

Alibaba · model passport

Qwen3 Max Preview

qwen3-max-preview
  • Cloud only
  • Proprietary licence
  • Released 2025-09-05(curated)
5/27axes covered
Overall · LMArena
1,434#95 of 396
Best percentile
76.8Hard prompts
Cohort standing
63.4median 51.9

What the data says

Benchmarked on 5 of 27 tracked axes. Every figure below is the model's own published result on that board.

Uneven: 23.9 percentile points between its best and worst axis — 76.8 pct on Hard prompts versus 52.9 pct on Factuality Arena.

  • Hard prompts76.8 pct1,458Verify →
  • Instruction following76.5 pct1,424Verify →
  • Overall76.3 pct1,434Verify →
  • Coding74.7 pct1,480Verify →
  • Factuality Arena52.9 pct1,441Verify →
  • WebDev ArenaNot benchmarked
  • Vision ArenaNot benchmarked
  • Search ArenaNot benchmarked
  • Document ArenaNot benchmarked
  • Agent ArenaNot benchmarked
  • GPQA DiamondNot benchmarked
  • AIME (math)Not benchmarked
  • FrontierMathNot benchmarked
  • SimpleQA VerifiedNot benchmarked
  • ARC-AGI-2Not benchmarked
  • Humanity's Last ExamNot benchmarked
  • SimpleBenchNot benchmarked
  • LiveBenchNot benchmarked
  • BFCL v4 (function calling)Not benchmarked
  • SWE-bench Verified (live board)Not benchmarked
  • Terminal-Bench 4.0Not benchmarked
  • MMLU-Pro (Artificial Analysis)Not benchmarked
  • LiveCodeBench (Artificial Analysis)Not benchmarked
  • IFBench (Artificial Analysis)Not 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-preview stands at 63.4 (raw mean 71.4) — measured on 5 of 27 axes.

    standingtemplateVerify →

  • qwen3-max-preview stands at 63.4 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 →