Skip to content
llmwaves

Qwen3.6 35B A3B

Qwen · released Apr 27, 2026

Open weightsReasoningTool useStructured outputVisionVideo in

Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated...

Specification

Context window
262K
Max output
262K
Knowledge cutoff
Not stated
Parameters
36B
Licence
apache-2.0
Serving providers
9
Moderated
No
Uptime
100.0%

Intelligence

32.1

77th percentile

Coding

41.9

Coding Index

Agentic

21.6

Agentic Index

Output speed

177 t/s

Median across providers

Latency

254ms

Time to first token

Cost per task

$0.09

Estimated

Benchmarks

Where the score comes from

The Intelligence Index is a composite. These are the underlying evaluations this model was actually measured on.

Evaluation scores

Percentage correct · higher is better

  • τ²-bench (Telecom)
    95.3%
  • GPQA Diamond
    84.1%
  • AA-LCR (long context)
    66.7%
  • IFBench
    64.4%
  • SciCode
    35.8%
  • Terminal-Bench Hard
    34.8%
  • Humanity's Last Exam
    22.2%

An evaluation missing from this list was not run for this model — it is not a zero.

View as table
EvaluationScore
τ²-bench (Telecom)95.3%
GPQA Diamond84.1%
AA-LCR (long context)66.7%
IFBench64.4%
SciCode35.8%
Terminal-Bench Hard34.8%
Humanity's Last Exam22.2%

Against its peers

Intelligence Index · this model highlighted, nearest peers in grey

Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.

View as table
ModelIntelligence
o3 Pro33.3
Qwen3.5-122B-A10B32.8
Qwen3 Max Thinking32.5
Qwen3.6 35B A3B32.1
M2.132.1
GPT-5.1-Codex-Mini31.3
Ring-2.6-1T31.1
o331.1

Percentile among all indexed models

Intelligence77th
Coding54th
Agentic37th
Terminal work80th

Pricing

What it costs to run

List prices per million tokens, plus what one representative task works out to.

List price

Input / 1M tokens
$0.14
Output / 1M tokens
$1
Cached input / 1M
$0.05
Blended 3:1
$0.355

One task, estimated

$0.09

Input tokens
50,000
Output tokens
80,000
Profile
Reasoning

Estimated from list pricing: 50K input tokens plus 80K output tokens for reasoning models (25K for non-reasoning).

Serving providers

Speed and latency figures are medians across these providers, so a widely-served model reports a blend rather than any single endpoint.