- Intelligence
- 32.6
- Rank 111 of 744 measured models
- Coding
- 70.1
- Rank 55 of 298 measured models
- Output speed
- 177 t/s
- Rank 51 of 403 measured models
- Price/1M
- $3.38
- Rank 506 of 659 measured models
- Context window
- 1M
- Rank 84 of 1199 measured models
- Cost per task
- $3.69
- Rank 180 of 193 measured models
Gemini 3.5 Flash (High) scores 32.6 on the Artificial Analysis Intelligence Index, ranking 111th of 744 measured models. The closest models on this index are GPT-5.3 Codex (Xhigh) (32.5), Motif 3 (Beta) (32.3), and Claude Opus 4.6 (batch) (31.9). At $3.38 per million tokens (3:1 input/output blended price), it is cheaper than GPT-5.3 Codex (Xhigh) ($4.81). With an output speed of 177 t/s, it is faster than GPT-5.3 Codex (Xhigh) (98.5 t/s).
Additional benchmarks21
Design Arena · 3d55.9%
Design Arena · Agenticgamedev55.4%
Design Arena · Agentichtmlslides45.8%
Design Arena · Agenticslides Html45.7%
Design Arena · Agenticslides Python Pptx57.8%
Design Arena · Agenticslides57.5%
Design Arena · Androidnative57.7%
Design Arena · Asciiart58.9%
Design Arena · Codecategories54.1%
Design Arena · Dataviz53.0%
Design Arena · Fullstack56.2%
Design Arena · Gamedev53.0%
Design Arena · Godotgamedev43.0%
Design Arena · Htmlslides46.5%
Design Arena · Mobileapps51.2%
Design Arena · Pptxslides57.7%
Design Arena · Python Pptxslides57.4%
Design Arena · Svg58.3%
Design Arena · Uicomponent54.5%
Design Arena · Webapps52.6%
Design Arena · Website53.8%
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- Motif 3
Motif Technologies · — · —
33.6+1.0——Compare - GPT-5.3 Codex (Xhigh)
OpenAI · $4.81 · 98.5 t/s
32.5−0.1$4.8198.5 t/sCompare - Motif 3 (Beta)
Motif Technologies · — · —
32.3−0.3——Compare - Claude Opus 4.6 (batch)
Anthropic · — · —
31.9−0.7——Compare
