Skip to content
aiqbench

Alibaba · model passport

Qwen3 Coder 480b A35b Instruct

qwen3-coder-480b-a35b-instruct
  • Open weights
  • Apache 2.0 licence
  • 480.2B params
  • Released 2025-07-22(curated)
11/27axes covered
Overall · LMArena
1,388#166 of 396
Best percentile
66.0LiveBench
Cohort standing
48.8median 51.8

What the data says

Benchmarked on 11 of 27 tracked axes. Every figure below is the model's own published result on that board.

Uneven: 49.5 percentile points between its best and worst axis — 66 pct on LiveBench versus 16.5 pct on WebDev Arena.

  • LiveBench66 pct61.7%Verify →
  • Coding65.7 pct1,457Verify →
  • MMLU-Pro (Artificial Analysis)62.2 pct78.8%Verify →
  • LiveCodeBench (Artificial Analysis)61.8 pct58.5%Verify →
  • Instruction following61.1 pct1,383Verify →
  • Hard prompts60.1 pct1,414Verify →
  • Overall58.3 pct1,388Verify →
  • IFBench (Artificial Analysis)41.7 pct40.5%Verify →
  • Terminal-Bench22.7 pct27.2%Verify →
  • Factuality Arena16.9 pct1,400Verify →
  • WebDev Arena16.5 pct1,275Verify →
  • 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
  • BFCL v4 (function calling)Not benchmarked
  • SWE-bench Verified (live board)Not benchmarked
  • Terminal-Bench 4.0Not benchmarked
  • HHEM Hallucination (Vectara)Not benchmarked
  • SWE-bench VerifiedNot 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-Coder-480B-A35B-Instruct
Parameters480.2B
ArchitectureQwen3MoeForCausalLM
LicenceApache 2.0

Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "Qwen/Qwen3-Coder-480B-A35B-Instruct"
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-coder-480b-a35b-instruct stands at 48.8 (raw mean 48.5) — measured on 11 of 27 axes.

    standingtemplateVerify →

  • qwen3-coder-480b-a35b-instruct stands at 48.8 versus a cohort median of 51.8 across 146 models released within 180 days — below 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 →