Back

Alibaba

Qwen3 VL 8B Instruct

Open weightsHugging Face
Intelligence
7.3
Rank 549 of 744 measured models
Output speed
118 t/s
Rank 136 of 403 measured models
Price/1M
$0.31
Rank 212 of 659 measured models
Context window
256K
Rank 518 of 1199 measured models

Qwen3 VL 8B Instruct scores 7.3 on the Artificial Analysis Intelligence Index, ranking 549th of 744 measured models. The closest models on this index are Gemini 2.0 Flash-Lite (Preview) (7.3), GPT-4o (May '24) (7.3), and Kimi Linear 48B A3B Instruct (7.3). At $0.31 per million tokens (3:1 input/output blended price), it is cheaper than GPT-4o (May '24) ($7.50). With an output speed of 118 t/s, it is slower than GPT-4o (May '24) (133 t/s).

Artificial Analysis Indices
Intelligence7.3
Rank 549 of 744 measured models
Math27.3
Rank 191 of 270 measured models
Standard Benchmarks
MMLU Pro68.6%
Rank 235 of 349 measured models
GPQA Diamond42.7%
Rank 510 of 619 measured models
HLE2.7%
Rank 656 of 664 measured models
LiveCodeBench33.2%
Rank 208 of 343 measured models
AIME 202527.3%
Rank 191 of 270 measured models
IFBench32.3%
Rank 363 of 450 measured models
AA-LCR16.7%
Rank 465 of 575 measured models
TerminalBench Hard2.3%
Rank 338 of 432 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