Skip to content
llmwaves

Qwen3.8 Max

Qwen · released Aug 3, 2026

ProprietaryReasoningTool useStructured outputVisionVideo in

Qwen3.8 Max is the flagship model in Alibaba's Qwen3.8 series, the general-availability successor to the Qwen3.8 Max Preview. It is a multimodal reasoning model intended for complex reasoning, visual understanding,...

Specification

Context window
1M
Max output
131K
Knowledge cutoff
Not stated
Parameters
Undisclosed
Licence
Proprietary
Serving providers
1
Moderated
No
Uptime
100.0%

Intelligence

58.1

99th percentile

Coding

71.8

Coding Index

Agentic

58.4

Agentic Index

Output speed

38 t/s

Median across providers

Latency

2.9s

Time to first token

Cost per task

$0.58

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

  • GPQA Diamond
    92.7%
  • AA-LCR (long context)
    74.3%
  • SciCode
    52.9%
  • τ²-bench (Telecom)
    51.3%
  • Humanity's Last Exam
    43.0%

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

View as table
EvaluationScore
GPQA Diamond92.7%
AA-LCR (long context)74.3%
SciCode52.9%
τ²-bench (Telecom)51.3%
Humanity's Last Exam43.0%

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
GPT-5.6 Sol60.9
Kimi K359.7
Qwen3.8 Max58.1
Claude Opus 4.857.3
Muse Spark 1.256.8
GPT-5.6 Terra56.6
GPT-5.556.3
Grok 4.555.8

Percentile among all indexed models

Intelligence99th
Coding92th
Agentic98th

Pricing

What it costs to run

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

List price

Input / 1M tokens
$2
Output / 1M tokens
$6
Cached input / 1M
$0.25
Blended 3:1
$3

One task, estimated

$0.58

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.