Back
FR

AI9Stars

G9v3-39A5B

ReasoningOpen weightsHugging Face
Intelligence
21.8
Rank 225 of 768 measured models
Coding
33.1
Rank 177 of 299 measured models
Context window
131K
Rank 868 of 1296 measured models

G9v3-39A5B scores 21.8 on the Artificial Analysis Intelligence Index, ranking 225th of 768 measured models. The closest models on this index are o3-pro (21.9), MiMo-V2.5 (21.8), and KAT Coder Pro V2 (21.7).

Artificial Analysis Indices
Intelligence21.8
Rank 225 of 768 measured models
Coding33.1
Rank 177 of 299 measured models
Standard Benchmarks
GPQA Diamond80.5%
Rank 204 of 620 measured models
HLE17.5%
Rank 258 of 681 measured models
SciCode36.8%
Rank 208 of 248 measured models
AA-LCR65.3%
Rank 269 of 592 measured models
Terminal-Bench 2.132.6%
Rank 158 of 245 measured models
τ-Bench Banking22.1%
Rank 93 of 211 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