Back

Google

DiffusionGemma 26B A4B

ReasoningOpen weightsHugging Face
Intelligence
9.5
Rank 441 of 744 measured models
Coding
19.7
Rank 234 of 298 measured models
Context window
256K
Rank 518 of 1199 measured models

DiffusionGemma 26B A4B scores 9.5 on the Artificial Analysis Intelligence Index, ranking 441st of 744 measured models. The closest models on this index are GPT-4.5 (Preview) (9.6), Qwen3 VL 30B A3B (Reasoning) (9.5), and Qwen3 VL 30B A3B Thinking (9.5).

Artificial Analysis Indices
Intelligence9.5
Rank 441 of 744 measured models
Coding19.7
Rank 234 of 298 measured models
Standard Benchmarks
GPQA Diamond66.9%
Rank 353 of 619 measured models
HLE10.8%
Rank 320 of 664 measured models
IFBench59.5%
Rank 131 of 450 measured models
AA-LCR19.7%
Rank 454 of 575 measured models
Terminal-Bench 2.112.4%
Rank 196 of 244 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