Skip to content
aiqbench

Alibaba · model passport

Qwen3 235b A22b Instruct 2507

qwen3-235b-a22b-instruct-2507
  • Open weights
  • Apache 2.0 licence
  • 235.1B params
  • Released 2025-07-01(from model name)
8/27axes covered
Overall · LMArena
1,422#116 of 396
Best percentile
76.8BFCL v4 (function calling)
Cohort standing
57.0median 51.6

What the data says

Benchmarked on 8 of 27 tracked axes. Every figure below is the model's own published result on that board.

Uneven: 56.6 percentile points between its best and worst axis — 76.8 pct on BFCL v4 (function calling) versus 20.2 pct on ARC-AGI-2.

  • BFCL v4 (function calling)Dormant board76.8 pct52.1%Verify →
  • Hard prompts74 pct1,447Verify →
  • Coding72.1 pct1,472Verify →
  • Instruction following72 pct1,414Verify →
  • Overall71 pct1,422Verify →
  • LiveBench51.2 pct54.0%Verify →
  • Factuality Arena39.5 pct1,431Verify →
  • ARC-AGI-220.2 pct1.3%Verify →
  • 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
  • Humanity's Last ExamNot benchmarked
  • SimpleBenchNot 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.

How to run it

Run it yourself

RepositoryQwen/Qwen3-235B-A22B-Instruct-2507
Parameters235.1B
ArchitectureQwen3MoeForCausalLM
LicenceApache 2.0

Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "Qwen/Qwen3-235B-A22B-Instruct-2507"
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-instruct-2507 stands at 57 (raw mean 59.6) — measured on 8 of 27 axes.

    standingtemplateVerify →

  • qwen3-235b-a22b-instruct-2507 stands at 57 versus a cohort median of 51.6 across 144 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 →