Skip to content
aiqbench

Alibaba · model passport

Qwen3 6 Max Preview

qwen3-6-max-preview
  • Cloud only
  • Proprietary licence
  • Released 2026-10-13(first seen on LMArena)
13/27axes covered
Overall · LMArena
1,461#53 of 396
Best percentile
95.1IFBench (Artificial Analysis)
Cohort standing
72.5median 60.6

What the data says

Benchmarked on 13 of 27 tracked axes. Every figure below is the model's own published result on that board.

Strongest axes

  • 95.1 pct — IFBench (Artificial Analysis) (76.6%)
  • 87.5 pct — Coding (1,512)
  • 86.9 pct — Overall (1,461)

Uneven: 35.4 percentile points between its best and worst axis — 95.1 pct on IFBench (Artificial Analysis) versus 59.7 pct on WebDev Arena.

  • IFBench (Artificial Analysis)95.1 pct76.6%Verify →
  • Coding87.5 pct1,512Verify →
  • Overall86.9 pct1,461Verify →
  • Instruction following86.9 pct1,452Verify →
  • Hard prompts86.4 pct1,483Verify →
  • SimpleBench80.5 pct63.0%Verify →
  • SWE-bench Verified75 pct76.7%Verify →
  • GPQA Diamond73.3 pct87.4%Verify →
  • AIME (math)73 pct91.1%Verify →
  • SimpleQA Verified72 pct52.0%Verify →
  • Factuality Arena69.8 pct1,453Verify →
  • FrontierMath63.8 pct23.1%Verify →
  • WebDev Arena59.7 pct1,483Verify →
  • Vision ArenaNot benchmarked
  • Search ArenaNot benchmarked
  • Document ArenaNot benchmarked
  • Agent ArenaNot benchmarked
  • ARC-AGI-2Not benchmarked
  • Humanity's Last ExamNot 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
  • HHEM Hallucination (Vectara)Not 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.

  • qwen3.6-max-preview stands at 72.5 (raw mean 77.7) — measured on 13 of 27 axes.

    standingtemplateVerify →

  • qwen3.6-max-preview stands at 72.5 versus a cohort median of 60.6 across 168 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 →