Back

Alibaba

Qwen3 VL 30B A3B (Reasoning)

ReasoningOpen weights
Intelligence
9.5
Rank 441 of 744 measured models
Output speed
114 t/s
Rank 148 of 403 measured models
Price/1M
$0.50
Rank 277 of 659 measured models
Context window
256K
Rank 518 of 1199 measured models

Qwen3 VL 30B A3B (Reasoning) scores 9.5 on the Artificial Analysis Intelligence Index, ranking 441st of 744 measured models. The closest models on this index are DiffusionGemma 26B A4B (9.5), Qwen3 VL 30B A3B Thinking (9.5), and QwQ 32B (9.5). At $0.50 per million tokens (3:1 input/output blended price), it is cheaper than QwQ 32B ($0.745), more expensive than Qwen3 VL 30B A3B Thinking ($0.467).

Artificial Analysis Indices
Intelligence9.5
Rank 441 of 744 measured models
Math82.3
Rank 58 of 270 measured models
Standard Benchmarks
MMLU Pro80.7%
Rank 103 of 349 measured models
GPQA Diamond72.0%
Rank 303 of 619 measured models
HLE8.9%
Rank 353 of 664 measured models
LiveCodeBench69.7%
Rank 70 of 343 measured models
AIME 202582.3%
Rank 58 of 270 measured models
IFBench45.1%
Rank 219 of 450 measured models
TerminalBench Hard5.3%
Rank 292 of 432 measured models
τ²-Bench19.9%
Rank 356 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