- Intelligence
- 34.0
- Rank 103 of 750 measured models
- Coding
- 69.2
- Rank 57 of 298 measured models
- Output speed
- 209 t/s
- Rank 48 of 411 measured models
- Price/1M
- $1.50
- Rank 438 of 673 measured models
- Context window
- 1M
- Rank 86 of 1218 measured models
- Cost per task
- $1.60
- Rank 159 of 199 measured models
Gemini 3.6 Flash (High) scores 34.0 on the Artificial Analysis Intelligence Index, ranking 103rd of 750 measured models. The closest models on this index are DeepSeek V4 Flash 0731 (Max) (34.3), JT-4.1 Flash 236B A21B (33.9), and GLM-5.2 (33.7). At $1.50 per million tokens (3:1 input/output blended price), it is cheaper than GLM-5.2 ($2.15), more expensive than DeepSeek V4 Flash 0731 (Max) ($0.175). With an output speed of 209 t/s, it is faster than DeepSeek V4 Flash 0731 (Max) (145 t/s) and GLM-5.2 (87.8 t/s).
Additional benchmarks15
Design Arena · 3d52.9%
Design Arena · Agenticgamedev47.8%
Design Arena · Androidnative53.7%
Design Arena · Asciiart57.1%
Design Arena · Codecategories53.3%
Design Arena · Dataviz52.3%
Design Arena · Fullstack44.3%
Design Arena · Gamedev51.0%
Design Arena · Htmlslides41.9%
Design Arena · Mobileapps50.1%
Design Arena · Python Pptxslides38.8%
Design Arena · Spreadsheet50.0%
Design Arena · Uicomponent53.9%
Design Arena · Webapps45.5%
Design Arena · Website55.4%
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- DeepSeek V4 Flash 0731 (Max)
DeepSeek · $0.175 · 145 t/s
34.3+0.3$0.175145 t/sCompare - JT-4.1 Flash 236B A21B
China Mobile · — · —
33.9−0.1——Compare - GLM-5.2
Z.AI · $2.15 · 87.8 t/s
33.7−0.3$2.1587.8 t/sCompare - Muse Spark 1.1 (Xhigh)
Meta · $2 · 280 t/s
33.7−0.3$2280 t/sCompare
