Back

Alibaba

Qwen3 VL 32B Instruct

Open weightsHugging Face
Intelligence
8.4
Rank 490 of 744 measured models
Output speed
91.1 t/s
Rank 195 of 403 measured models
Price/1M
$0.28
Rank 203 of 659 measured models
Context window
256K
Rank 518 of 1199 measured models

Qwen3 VL 32B Instruct scores 8.4 on the Artificial Analysis Intelligence Index, ranking 490th of 744 measured models. The closest models on this index are DeepSeek R1 Distill Qwen 32B (8.4), GLM-4.6V (8.4), and GPT-4o (2024-11-20) (8.4). At $0.28 per million tokens (3:1 input/output blended price), it is cheaper than GLM-4.6V ($0.45) and GPT-4o (2024-11-20) ($4.38). With an output speed of 91.1 t/s, it is faster than GLM-4.6V (82.1 t/s).

Artificial Analysis Indices
Intelligence8.4
Rank 490 of 744 measured models
Math68.3
Rank 101 of 270 measured models
Standard Benchmarks
MMLU Pro79.1%
Rank 130 of 349 measured models
GPQA Diamond67.1%
Rank 350 of 619 measured models
HLE6.8%
Rank 396 of 664 measured models
LiveCodeBench51.4%
Rank 145 of 343 measured models
AIME 202568.3%
Rank 101 of 270 measured models
IFBench39.2%
Rank 285 of 450 measured models
TerminalBench Hard8.3%
Rank 249 of 432 measured models
τ²-Bench29.2%
Rank 281 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