Qwen3 VL 30B A3B Instruct
Qwen · released Oct 6, 2025
Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-following for general multimodal tasks. It excels in perception...
Specification
- Context window
- 262K
- Max output
- 16K
- Knowledge cutoff
- Mar 31, 2025
- Parameters
- 31.1B
- Licence
- apache-2.0
- Serving providers
- 4
- Moderated
- No
- Uptime
- 100.0%
Intelligence
9.9
35th percentile
Coding
—
Coding Index
Agentic
—
Agentic Index
Output speed
16 t/s
Median across providers
Latency
417ms
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-Pro76.4%
- AIME 202572.3%
- GPQA Diamond69.5%
- LiveCodeBench47.6%
- IFBench33.1%
- SciCode30.8%
- AA-LCR (long context)27.3%
- τ²-bench (Telecom)19.0%
- Humanity's Last Exam6.3%
- Terminal-Bench Hard6.1%
An evaluation missing from this list was not run for this model — it is not a zero.
View as table
| Evaluation | Score |
|---|---|
| MMLU-Pro | 76.4% |
| AIME 2025 | 72.3% |
| GPQA Diamond | 69.5% |
| LiveCodeBench | 47.6% |
| IFBench | 33.1% |
| SciCode | 30.8% |
| AA-LCR (long context) | 27.3% |
| τ²-bench (Telecom) | 19.0% |
| Humanity's Last Exam | 6.3% |
| Terminal-Bench Hard | 6.1% |
Against its peers
Intelligence Index · this model highlighted, nearest peers in grey
- Llama 4 ScoutMeta10.3
- Qwen3 VL 30B A3B InstructQwen9.9
- R1 Distill Llama 70BDeepSeek9.8
- GPT-4.1 NanoOpenAI9.6
- SonarPerplexity9.4
- 9.4
- GPT-4o (2024-08-06)OpenAI9.4
- Sonar ProPerplexity9.1
Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.
View as table
| Model | Intelligence |
|---|---|
| Llama 4 Scout | 10.3 |
| Qwen3 VL 30B A3B Instruct | 9.9 |
| R1 Distill Llama 70B | 9.8 |
| GPT-4.1 Nano | 9.6 |
| Sonar | 9.4 |
| Qwen2.5 72B Instruct | 9.4 |
| GPT-4o (2024-08-06) | 9.4 |
| Sonar Pro | 9.1 |
Percentile among all indexed models
Pricing
What it costs to run
List prices per million tokens, plus what one representative task works out to.
List price
- Input / 1M tokens
- $0.15
- Output / 1M tokens
- $0.6
- Cached input / 1M
- Not offered
- Blended 3:1
- $0.262
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.