Alibaba

Qwen3 VL 4B Instruct

Intelligence
5.7
Rank 685 of 782 measured models
Context window
256K
Rank 583 of 1325 measured models

Qwen3 VL 4B Instruct scores 5.7 on the Artificial Analysis Intelligence Index, ranking 685th of 782 measured models. The closest models on this index are Jamba Reasoning 3B (5.7), Llama 2 Chat 7B (5.7), and MiniCPM-V 4.6 1.3B (5.7).

Artificial Analysis Indices
Intelligence5.7
Rank 685 of 782 measured models
Math37.0
Rank 168 of 270 measured models
Standard Benchmarks
MMLU Pro63.4%
Rank 261 of 349 measured models
GPQA Diamond37.1%
Rank 541 of 621 measured models
HLE3.6%
Rank 636 of 682 measured models
LiveCodeBench29.0%
Rank 230 of 343 measured models
AIME 202537.0%
Rank 168 of 270 measured models
IFBench31.8%
Rank 370 of 451 measured models
AA-LCR14.0%
Rank 493 of 593 measured models
TerminalBench Hard0.0%
Rank 385 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