Back
FR

Alibaba

Qwen3 4B 2507 Instruct

Intelligence
6.7
Rank 612 of 782 measured models
Context window
262K
Rank 449 of 1325 measured models

Qwen3 4B 2507 Instruct scores 6.7 on the Artificial Analysis Intelligence Index, ranking 612th of 782 measured models. The closest models on this index are GPT-4 (6.7), Hermes 4 - Llama-3.1 70B (6.7), and Mistral Small 3 (6.7).

Artificial Analysis Indices
Intelligence6.7
Rank 612 of 782 measured models
Math52.3
Rank 137 of 270 measured models
Standard Benchmarks
MMLU Pro67.2%
Rank 243 of 349 measured models
GPQA Diamond51.7%
Rank 460 of 621 measured models
HLE4.5%
Rank 539 of 682 measured models
LiveCodeBench37.7%
Rank 191 of 343 measured models
AIME 202552.3%
Rank 137 of 270 measured models
IFBench33.5%
Rank 347 of 451 measured models
AA-LCR11.3%
Rank 501 of 593 measured models
TerminalBench Hard4.5%
Rank 299 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