Gemini 3.7 Flash
ReasoningClosed weights
- Intelligence
- 36.9
- Rank 85 of 744 measured models
- Coding
- 71.0
- Rank 53 of 298 measured models
- Output speed
- 304 t/s
- Rank 11 of 403 measured models
- Price/1M
- $1.50
- Rank 426 of 659 measured models
- Context window
- 1M
- Rank 84 of 1199 measured models
Gemini 3.7 Flash (Low) scores 36.9 on the Artificial Analysis Intelligence Index, ranking 85th of 744 measured models. The closest models on this index are MiMo-V2.6-Flash (37.9), GPT-5.6 Luna (37.3), and DeepSeek V4 Pro 0813 (36.0). At $1.50 per million tokens (3:1 input/output blended price), it is cheaper than DeepSeek V4 Pro 0813 ($1.98), more expensive than MiMo-V2.6-Flash ($0.175) and GPT-5.6 Luna ($0.45). With an output speed of 304 t/s, it is faster than MiMo-V2.6-Flash (53.8 t/s), GPT-5.6 Luna (115 t/s), and DeepSeek V4 Pro 0813 (83.3 t/s).
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- GPT-6 Luna
OpenAI · $0.20 · 116 t/s
38.1+1.2$0.20116 t/sCompare - MiMo-V2.6-Flash
Xiaomi · $0.175 · 53.8 t/s
37.9+1.0$0.17553.8 t/sCompare - GPT-5.6 Luna
OpenAI · $0.45 · 115 t/s
37.3+0.4$0.45115 t/sCompare - DeepSeek V4 Pro 0813
DeepSeek · $1.98 · 83.3 t/s
36.0−0.9$1.9883.3 t/sCompare
