Back

Alibaba

Qwen3 4B 2507 (Reasoning)

ReasoningOpen weights
Intelligence
8.8
Rank 479 of 748 measured models
Context window
262K
Rank 463 of 1211 measured models

Qwen3 4B 2507 (Reasoning) scores 8.8 on the Artificial Analysis Intelligence Index, ranking 479th of 748 measured models. The closest models on this index are Claude 3.5 Haiku (8.9), MiniCPM5-1B (8.8), and Sarvam 105B (High) (8.8).

Artificial Analysis Indices
Intelligence8.8
Rank 479 of 748 measured models
Math82.7
Rank 56 of 270 measured models
Standard Benchmarks
MMLU Pro74.3%
Rank 187 of 349 measured models
GPQA Diamond66.7%
Rank 356 of 620 measured models
HLE6.2%
Rank 424 of 668 measured models
LiveCodeBench64.1%
Rank 101 of 343 measured models
AIME 202582.7%
Rank 56 of 270 measured models
IFBench49.8%
Rank 183 of 450 measured models
AA-LCR37.3%
Rank 385 of 579 measured models
TerminalBench Hard1.5%
Rank 358 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