- Intelligence
- 17.9
- Rank 272 of 744 measured models
- Output speed
- 195 t/s
- Rank 38 of 403 measured models
- Price/1M
- $1.13
- Rank 392 of 659 measured models
- Context window
- 1M
- Rank 84 of 1199 measured models
Gemini 3 Flash Preview (Non-reasoning) scores 17.9 on the Artificial Analysis Intelligence Index, ranking 272nd of 744 measured models. The closest models on this index are Qwen3.5 397B A17B (18.4), Qwen3.6 35B A3B (18.2), and Muse Glimmer (High) (17.5). At $1.13 per million tokens (3:1 input/output blended price), it is cheaper than Qwen3.5 397B A17B ($1.35), more expensive than Qwen3.6 35B A3B ($0.844) and Muse Glimmer (High) ($0.525). With an output speed of 195 t/s, it is faster than Qwen3.5 397B A17B (55.9 t/s), Qwen3.6 35B A3B (127 t/s), and Muse Glimmer (High) (124 t/s).
Additional benchmarks12
Design Arena · 3d62.7%
Design Arena · Agenticslides Python Pptx39.3%
Design Arena · Agenticslides39.3%
Design Arena · Androidnative48.1%
Design Arena · Codecategories57.6%
Design Arena · Fullstack47.4%
Design Arena · Gamedev58.3%
Design Arena · Godotgamedev50.6%
Design Arena · Mobileapps46.6%
Design Arena · Python Pptxslides38.3%
Design Arena · Webapps48.5%
Design Arena · Website57.0%
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- Claude 4.1 Opus
Anthropic · $30 · —
18.6+0.7$30—Compare - Qwen3.5 397B A17B
Alibaba · $1.35 · 55.9 t/s
18.4+0.5$1.3555.9 t/sCompare - Qwen3.6 35B A3B
Alibaba · $0.844 · 127 t/s
18.2+0.3$0.844127 t/sCompare - Muse Glimmer (High)
Meta · $0.525 · 124 t/s
17.5−0.4$0.525124 t/sCompare
