Gemini 3.5 Flash Lite
Fast Gemini model balancing multimodal reasoning, tool use, and cost
ECI STANDING#77 of 266
SCORE145.13142.76–146.76 CI
FRONTIER LAGLaunched 15.1 months behindScores about what o3 did in April 2025.
SCORES LIKE THESE MODELSGPT-5 miniOpenAI · Aug 2025145.52
Full Epoch Capabilities Index ranking ↗Gemini 2.5 Pro (Jun 2025)Google DeepMind · Jun 2025145.26
DeepSeek-V3.2-ExpDeepSeek · Sep 2025145.02
Qwen3.7 FlashAlibaba · Jul 2026144.63RELEASE DATEJul 21, 2026
WEIGHTSClosed weights
CONTEXT WINDOW1.05M
MAX OUTPUT65.5K
REASONINGYes
TOOL CALLINGYes
INPUTStext, image, video, audio, pdf
OUTPUTStext
Specifications from Models.dev. Availability and limits may differ by provider. Benchmark scores come from Epoch AI under CC BY 4.0.