- Intelligence
- 39.1
- Rank 73 of 744 measured models
- Coding
- 76.1
- Rank 23 of 298 measured models
- Output speed
- 299 t/s
- Rank 13 of 403 measured models
- Price/1M
- $1.50
- Rank 426 of 659 measured models
- Context window
- 1M
- Rank 84 of 1199 measured models
- Cost per task
- $0.925
- Rank 125 of 193 measured models
Gemini 3.7 Flash (High) scores 39.1 on the Artificial Analysis Intelligence Index, ranking 73rd of 744 measured models. The closest models on this index are DeepSeek V4.1 Flash (39.5), GPT-5.4 (39.0), and Grok 4.5 (High) (38.8). At $1.50 per million tokens (3:1 input/output blended price), it is cheaper than GPT-5.4 ($5.63) and Grok 4.5 (High) ($3), more expensive than DeepSeek V4.1 Flash ($0.525). With an output speed of 299 t/s, it is faster than DeepSeek V4.1 Flash (174 t/s), GPT-5.4 (85.5 t/s), and Grok 4.5 (High) (58.2 t/s).
Additional benchmarks14
Design Arena · 3d53.8%
Design Arena · Agenticgamedev52.1%
Design Arena · Androidnative53.3%
Design Arena · Asciiart55.6%
Design Arena · Codecategories53.9%
Design Arena · Dataviz55.3%
Design Arena · Fullstack43.5%
Design Arena · Gamedev53.5%
Design Arena · Godotgamedev50.8%
Design Arena · Mobileapps52.9%
Design Arena · Svg53.6%
Design Arena · Uicomponent52.2%
Design Arena · Webapps46.6%
Design Arena · Website54.0%
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- Muse Spark 1.2 (Xhigh)
Meta · $2 · 322 t/s
39.6+0.5$2322 t/sCompare - DeepSeek V4.1 Flash
DeepSeek · $0.525 · 174 t/s
39.5+0.4$0.525174 t/sCompare - GPT-5.4
OpenAI · $5.63 · 85.5 t/s
39.0−0.1$5.6385.5 t/sCompare - Grok 4.5 (High)
SpaceXSI · $3 · 58.2 t/s
38.8−0.3$358.2 t/sCompare
