Skip to content
aiqbench

Alibaba · model passport

Qwen3 235b A22b

qwen3-235b-a22b
  • Open weights
  • Apache 2.0 licence
  • 235.1B params
  • Released 2025-04-29(curated)
10/27axes covered
Overall · LMArena
1,375#177 of 396
Best percentile
82.4MMLU-Pro (Artificial Analysis)
Cohort standing
53.1median 48.6

What the data says

Benchmarked on 10 of 27 tracked axes. Every figure below is the model's own published result on that board.

Uneven: 57.1 percentile points between its best and worst axis — 82.4 pct on MMLU-Pro (Artificial Analysis) versus 25.3 pct on SimpleBench.

  • MMLU-Pro (Artificial Analysis)82.4 pct82.8%Verify →
  • LiveCodeBench (Artificial Analysis)65.6 pct62.2%Verify →
  • Coding56.5 pct1,432Verify →
  • HHEM Hallucination (Vectara)56.2 pct90.7%Verify →
  • Overall55.6 pct1,375Verify →
  • Hard prompts55.3 pct1,392Verify →
  • Instruction following53.8 pct1,357Verify →
  • GPQA Diamond52 pct70.7%Verify →
  • IFBench (Artificial Analysis)37 pct38.7%Verify →
  • SimpleBench25.3 pct31.0%Verify →
  • WebDev ArenaNot benchmarked
  • Vision ArenaNot benchmarked
  • Factuality ArenaNot benchmarked
  • Search ArenaNot benchmarked
  • Document ArenaNot benchmarked
  • Agent ArenaNot benchmarked
  • AIME (math)Not benchmarked
  • FrontierMathNot benchmarked
  • SimpleQA VerifiedNot 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
  • 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.

How to run it

Run it yourself

RepositoryQwen/Qwen3-235B-A22B
Parameters235.1B
ArchitectureQwen3MoeForCausalLM
LicenceApache 2.0

Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "Qwen/Qwen3-235B-A22B"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)

Ollama

We don't sync Ollama tags, so we won't print a command we can't verify — a wrong one would pull the wrong model. Search the Ollama library →

Unsloth fine-tuning recipes are model-specific and we don't derive them here. Unsloth docs →

Identifiers, limits and prices are synced from the upstream source shown above. Any field we haven't synced is left out entirely rather than guessed.

  • qwen3-235b-a22b stands at 53.1 (raw mean 54) — measured on 10 of 27 axes.

    standingtemplateVerify →

  • qwen3-235b-a22b stands at 53.1 versus a cohort median of 48.6 across 150 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 →