Skip to content
llmwaves

Qwen3.5-122B-A10B

Qwen · released Feb 25, 2026

Open weightsReasoningTool useStructured outputVisionVideo in

The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of...

Specification

Context window
262K
Max output
66K
Knowledge cutoff
Not stated
Parameters
125.1B
Licence
apache-2.0
Serving providers
4
Moderated
No
Uptime
100.0%

Intelligence

15.6

59th percentile

Coding

45.7

Coding Index

Agentic

7.6

Agentic Index

Output speed

72 t/s

Median across providers

Latency

971ms

Time to first token

Cost per task

$0.18

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)
    93.6%
  • GPQA Diamond
    85.7%
  • AA-LCR (long context)
    76.3%
  • IFBench
    75.7%
  • SciCode
    39.7%
  • Terminal-Bench Hard
    31.1%
  • Humanity's Last Exam
    25.2%

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

View as table
EvaluationScore
τ²-bench (Telecom)93.6%
GPQA Diamond85.7%
AA-LCR (long context)76.3%
IFBench75.7%
SciCode39.7%
Terminal-Bench Hard31.1%
Humanity's Last Exam25.2%

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
V3.216.0
Qwen3.5-122B-A10B15.6
Gemini 3.1 Flash Lite15.6
Gemini 3.1 Flash Lite Preview15.6
Claude Haiku 4.515.4
Kimi K2 090515.3
gpt-oss-20b (free)15.2
o115.2

Percentile among all indexed models

Intelligence59th
Coding52th
Agentic27th
Terminal work73th

Pricing

What it costs to run

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

List price

Input / 1M tokens
$0.26
Output / 1M tokens
$2.08
Cached input / 1M
Not offered
Blended 3:1
$0.715

One task, estimated

$0.18

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.