Back

Google

Gemini 2.5 Flash Preview (Sep '25)

Closed weights
Intelligence
12.4
Rank 367 of 744 measured models
Context window
1M
Rank 84 of 1199 measured models

Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning) scores 12.4 on the Artificial Analysis Intelligence Index, ranking 367th of 744 measured models. The closest models on this index are MiniCPM5-2B (12.5), o3 Mini (batch) (12.5), and o1-pro (12.4).

Artificial Analysis Indices
Non-reasoning
Intelligence12.4
Rank 367 of 744 measured models
Math56.7
Rank 126 of 270 measured models
Standard Benchmarks
MMLU Pro83.6%
Rank 52 of 349 measured models
GPQA Diamond76.6%
Rank 247 of 619 measured models
HLE8.7%
Rank 358 of 664 measured models
LiveCodeBench62.5%
Rank 109 of 343 measured models
AIME 202556.7%
Rank 126 of 270 measured models
IFBench43.5%
Rank 235 of 450 measured models
AA-LCR60.0%
Rank 287 of 575 measured models
TerminalBench Hard14.4%
Rank 209 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