Back

Alibaba

Qwen3 VL 30B A3B Instruct

Open weightsModels.devHugging Face
Intelligence
7.9
Rank 506 of 744 measured models
Output speed
23.8 t/s
Rank 396 of 403 measured models
Price/1M
$0.412
Rank 245 of 659 measured models
Context window
256K
Rank 518 of 1199 measured models

Qwen3 VL 30B A3B Instruct scores 7.9 on the Artificial Analysis Intelligence Index, ranking 506th of 744 measured models. The closest models on this index are Claude 3.5 Sonnet (Oct '24) (7.9), DeepSeek R1 Distill Llama 70B (7.9), and Gemini 1.5 Pro (Sep '24) (7.9). At $0.412 per million tokens (3:1 input/output blended price), it is cheaper than Claude 3.5 Sonnet (Oct '24) ($6) and DeepSeek R1 Distill Llama 70B ($0.80).

Artificial Analysis Indices
Intelligence7.9
Rank 506 of 744 measured models
Math72.3
Rank 91 of 270 measured models
Standard Benchmarks
MMLU Pro76.4%
Rank 161 of 349 measured models
GPQA Diamond69.5%
Rank 327 of 619 measured models
HLE6.3%
Rank 415 of 664 measured models
LiveCodeBench47.6%
Rank 155 of 343 measured models
AIME 202572.3%
Rank 91 of 270 measured models
IFBench33.1%
Rank 352 of 450 measured models
TerminalBench Hard6.1%
Rank 281 of 432 measured models
τ²-Bench19.0%
Rank 364 of 440 measured models
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.

Preferences and analytics

Rybbit: visits, performance, clicks, copies, forms and session replay (masked inputs), with your permission. Refusing does not limit the site.

Privacy

Allow navigation analytics?

With your permission, Rybbit measures visits, performance and interactions (clicks, copies, forms), including session replay, to improve BenchSift. Input values are masked in replays. Refusing does not limit the site.

Your choice is stored for 180 days. Change it at any time using “Privacy preferences” in the footer. Withdrawal reloads the page.

No choice stored: Rybbit is disabled.

Privacy