Gemini 2.5 Flash-Lite
ReasoningClosed weights
- Intelligence
- 8.5
- Rank 491 of 747 measured models
- Output speed
- 370 t/s
- Rank 8 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 (Reasoning) scores 8.5 on the Artificial Analysis Intelligence Index, ranking 491st of 747 measured models. The closest models on this index are Devstral 2 (8.6), DeepSeek V3 (Dec '24) (8.5), and DeepSeek R1 Distill Qwen 32B (8.4). At $0.175 per million tokens (3:1 input/output blended price), it is cheaper than DeepSeek V3 (Dec '24) ($0.463). With an output speed of 370 t/s, it is faster than Devstral 2 (139 t/s) and DeepSeek V3 (Dec '24) (37 t/s).
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- Devstral 2
Mistral · — · 139 t/s
8.6+0.1—139 t/sCompare - DeepSeek V3 (Dec '24)
DeepSeek · $0.463 · 37 t/s
8.5$0.46337 t/sCompare - DeepSeek R1 Distill Qwen 32B
DeepSeek · — · —
8.4−0.1——Compare - GLM-4.6V
Z.AI · $0.45 · 68.1 t/s
8.4−0.1$0.4568.1 t/sCompare
