Skip to content
aiqbench

Alibaba · model passport

Qwen3 235b A22b Instruct

qwen3-235b-a22b-instruct
  • Open weights
  • Apache 2.0 licence
  • Released 2026-10-28(first seen on LMArena (approximate))
5/27axes covered
Overall · LMArena
1,422#130 of 469
Best percentile
75.5Hard prompts
Cohort standing
61.0median 57.4

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: 32.7 percentile points between its best and worst axis — 75.5 pct on Hard prompts versus 42.8 pct on Factuality Arena.

  • Hard prompts75.5 pct1,447Verify →
  • Coding73.9 pct1,472Verify →
  • Instruction following73.6 pct1,414Verify →
  • Overall72.5 pct1,422Verify →
  • Factuality Arena42.8 pct1,431Verify →
  • 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.

  • Qwen3-235B-A22B-Instruct (2507) from alibaba covers 5 of 27 axes with a composite score of 67.6 and a shrunk score of 61, without thin coverage.

    standingVerify →

  • Qwen3-235B-A22B-Instruct (2507) from alibaba holds a standing of 61, which is above the cohort median standing of 57.4 within a cohort size of 215 models over a window of 180 days.

    cohortVerify →

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 →