Skip to content
aiqbench

Alibaba · model passport

Qwen: Qwen3.5-122B-A10B

qwen3-5-122b-a10b
  • Open weights
  • Apache 2.0 licence
  • 125.1B params
  • 262,144 context
  • Released 2026-02-24(HF repo created)
9/27axes covered
Overall · LMArena
1,416#124 of 396
Best percentile
92.6IFBench (Artificial Analysis)
Cohort standing
55.8median 57.4

What the data says

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

Strongest axes

  • 92.6 pct — IFBench (Artificial Analysis) (75.7%)

Uneven: 64.5 percentile points between its best and worst axis — 92.6 pct on IFBench (Artificial Analysis) versus 28.1 pct on WebDev Arena.

  • IFBench (Artificial Analysis)92.6 pct75.7%Verify →
  • Overall68.9 pct1,416Verify →
  • Instruction following68.9 pct1,406Verify →
  • Hard prompts67.4 pct1,433Verify →
  • Coding67 pct1,459Verify →
  • Vision Arena57.3 pct1,226Verify →
  • Factuality Arena36.6 pct1,428Verify →
  • HHEM Hallucination (Vectara)32.4 pct88.8%Verify →
  • WebDev Arena28.1 pct1,361Verify →
  • 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
  • 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/Qwen3.5-122B-A10B
Parameters125.1B
ArchitectureQwen3_5MoeForConditionalGeneration
LicenceApache 2.0

Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "Qwen/Qwen3.5-122B-A10B"
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/qwen3.5-122b-a10b
Context length262,144 tokens
Max output65,536 tokens
Acceptstext, image, video
Input price$0.26 per 1M tokens
Output price$2.08 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/qwen3.5-122b-a10b","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.

  • qwen3.5-122b-a10b stands at 55.8 (raw mean 57.7) — measured on 9 of 27 axes.

    standingtemplateVerify →

  • qwen3.5-122b-a10b stands at 55.8 versus a cohort median of 57.4 across 106 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 →