Skip to content
aiqbench

Alibaba · model passport

Qwen: Qwen3.5-35B-A3B

qwen3-5-35b-a3b
  • Open weights
  • Apache 2.0 licence
  • 36.0B params
  • 262,144 context
  • Released 2026-02-24(HF repo created)
10/27axes covered
Overall · LMArena
1,394#156 of 396
Best percentile
87.0IFBench (Artificial Analysis)
Cohort standing
51.5median 57.2

What the data says

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

Strongest axes

  • 87 pct — IFBench (Artificial Analysis) (72.5%)

Weakest axes

  • 12.9 pct — WebDev Arena (1,254)

Uneven: 74.1 percentile points between its best and worst axis — 87 pct on IFBench (Artificial Analysis) versus 12.9 pct on WebDev Arena.

  • IFBench (Artificial Analysis)87 pct72.5%Verify →
  • GPQA Diamond66.1 pct83.5%Verify →
  • Instruction following62.1 pct1,387Verify →
  • Overall60.9 pct1,394Verify →
  • Hard prompts59.3 pct1,412Verify →
  • Coding58.8 pct1,435Verify →
  • AIME (math)50 pct70.0%Verify →
  • HHEM Hallucination (Vectara)41.9 pct89.5%Verify →
  • Factuality Arena20.3 pct1,408Verify →
  • WebDev Arena12.9 pct1,254Verify →
  • Vision 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
  • MMLU-Pro (Artificial Analysis)Not benchmarked
  • LiveCodeBench (Artificial Analysis)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/Qwen3.5-35B-A3B
Parameters36.0B
ArchitectureQwen3_5MoeForConditionalGeneration
LicenceApache 2.0

Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "Qwen/Qwen3.5-35B-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/qwen3.5-35b-a3b
Context length262,144 tokens
Max output235,929 tokens
Acceptstext, image, video
Input price$0.15 per 1M tokens
Cached input price$0.05 per 1M tokens
Output price$1 per 1M tokens

API parameters this endpoint supports

Frequency penaltyInclude reasoningLogit biasLogprobsMax tokensMin-pPresence penaltyReasoningRepetition penaltyResponse formatSeedStop sequencesStructured outputsTemperatureTool choiceTool callingTop-kTop logprobsTop-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/qwen3.5-35b-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.

  • qwen3.5-35b-a3b stands at 51.5 (raw mean 51.9) — measured on 10 of 27 axes.

    standingtemplateVerify →

  • qwen3.5-35b-a3b stands at 51.5 versus a cohort median of 57.2 across 107 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 →