Back

Google

Gemini 2.5 Flash-Lite

ReasoningClosed weightsModels.dev
Intelligence
10.4
Rank 418 of 747 measured models
Output speed
325 t/s
Rank 10 of 405 measured models
Price/1M
$0.175
Rank 146 of 664 measured models
Context window
1M
Rank 84 of 1207 measured models

Gemini 2.5 Flash-Lite (Non-reasoning) scores 10.4 on the Artificial Analysis Intelligence Index, ranking 418th of 747 measured models. The closest models on this index are GPT-5 (ChatGPT) (10.4), Grok 3 Reasoning Beta (10.4), and Solar Open 100B (Reasoning) (10.4).

Artificial Analysis Indices
Non-reasoning
Intelligence10.4
Rank 418 of 747 measured models
Math35.3
Rank 174 of 270 measured models
Reasoning levels
Each point is a reasoning level of this model: more reasoning often raises the score but costs more. Select a point to open that level.
Intelligence Indexmost efficient ↗Price / 1M tokens
Standard Benchmarks
MMLU Pro72.4%
Rank 206 of 349 measured models
GPQA Diamond47.4%
Rank 485 of 620 measured models
HLE3.7%
Rank 614 of 667 measured models
LiveCodeBench40.0%
Rank 182 of 343 measured models
MATH-50092.6%
Rank 60 of 202 measured models
AIME 202450.0%
Rank 57 of 194 measured models
AIME 202535.3%
Rank 174 of 270 measured models
IFBench31.5%
Rank 373 of 450 measured models
Artificial Analysis media benchmarks
Text-to-speech ELO1,084 Elo
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