Skip to content
aiqbench

Alibaba · model passport

Qwen: Qwen3 30B A3B

qwen3-30b-a3b
  • Open weights
  • Apache 2.0 licence
  • 30.5B params
  • 40,960 context
  • Released 2025-04-29(curated)
9/27axes covered
Overall · LMArena
1,327#230 of 396
Best percentile
58.8MMLU-Pro (Artificial Analysis)
Cohort standing
47.6median 48.7

What the data says

Benchmarked on 9 of 27 tracked axes. Every figure below is the model's own published result on that board.

Uneven: 17.9 percentile points between its best and worst axis — 58.8 pct on MMLU-Pro (Artificial Analysis) versus 40.9 pct on Instruction following.

  • MMLU-Pro (Artificial Analysis)58.8 pct77.7%Verify →
  • LiveCodeBench (Artificial Analysis)56.5 pct50.6%Verify →
  • Coding46 pct1,385Verify →
  • AIME (math)45 pct62.8%Verify →
  • IFBench (Artificial Analysis)44.4 pct41.5%Verify →
  • Hard prompts44.2 pct1,344Verify →
  • GPQA Diamond43.4 pct61.7%Verify →
  • Overall42.2 pct1,327Verify →
  • Instruction following40.9 pct1,309Verify →
  • WebDev ArenaNot benchmarked
  • Vision ArenaNot benchmarked
  • Factuality ArenaNot benchmarked
  • Search ArenaNot benchmarked
  • Document ArenaNot benchmarked
  • Agent ArenaNot 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
  • 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/Qwen3-30B-A3B
Parameters30.5B
ArchitectureQwen3MoeForCausalLM
LicenceApache 2.0

Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "Qwen/Qwen3-30B-A3B"
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 →

Use it hosted

API model IDqwen/qwen3-30b-a3b
Context length40,960 tokens
Max output16,384 tokens
Input price$0.12 per 1M tokens
Output price$0.50 per 1M tokens

API parameters this endpoint supports

Frequency penaltyInclude reasoningLogit biasMax tokensMin-pPresence penaltyReasoningRepetition penaltyResponse formatSeedStop sequencesStructured outputsTemperatureTool choiceTool callingTop-kTop-p

Example request

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"qwen/qwen3-30b-a3b","messages":[{"role":"user","content":"Hello"}]}'

View on OpenRouter →

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.

  • qwen3-30b-a3b stands at 47.6 (raw mean 46.8) — measured on 9 of 27 axes.

    standingtemplateVerify →

  • qwen3-30b-a3b stands at 47.6 versus a cohort median of 48.7 across 150 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 →