Skip to content
llmwaves

Qwen3 VL 8B Instruct

Qwen · released Oct 14, 2025

Open weightsTool useStructured outputVision

Qwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built for high-fidelity understanding and reasoning across text, images, and video. It features improved multimodal fusion with Interleaved-MRoPE for long-horizon...

Specification

Context window
262K
Max output
33K
Knowledge cutoff
Not stated
Parameters
8.8B
Licence
apache-2.0
Serving providers
2
Moderated
No
Uptime
100.0%

Intelligence

8.2

28th percentile

Coding

Coding Index

Agentic

Agentic Index

Output speed

51 t/s

Median across providers

Latency

357ms

Time to first token

Cost per task

$0.02

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

  • MMLU-Pro
    68.6%
  • GPQA Diamond
    42.7%
  • LiveCodeBench
    33.2%
  • IFBench
    32.3%
  • τ²-bench (Telecom)
    29.2%
  • AIME 2025
    27.3%
  • SciCode
    17.4%
  • AA-LCR (long context)
    16.7%
  • Humanity's Last Exam
    2.7%
  • Terminal-Bench Hard
    2.3%

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

View as table
EvaluationScore
MMLU-Pro68.6%
GPQA Diamond42.7%
LiveCodeBench33.2%
IFBench32.3%
τ²-bench (Telecom)29.2%
AIME 202527.3%
SciCode17.4%
AA-LCR (long context)16.7%
Humanity's Last Exam2.7%
Terminal-Bench Hard2.3%

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
Sonar9.4
Sonar Pro9.1
GPT-4o (2024-05-13)8.4
Qwen3 VL 8B Instruct8.2
GPT-4 Turbo7.7
Command A7.5
Nemotron 3 Nano 30B A3B7.2
Mistral Large 24077.0

Percentile among all indexed models

Intelligence28th
Mathematics29th
Terminal work17th

Pricing

What it costs to run

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

List price

Input / 1M tokens
$0.117
Output / 1M tokens
$0.455
Cached input / 1M
Not offered
Blended 3:1
$0.202

One task, estimated

$0.02

Input tokens
50,000
Output tokens
25,000
Profile
Standard

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.