- Intelligence
- 15.6
- Rank 298 of 744 measured models
- Coding
- 34.7
- Rank 172 of 298 measured models
- Output speed
- 342 t/s
- Rank 7 of 403 measured models
- Price/1M
- $0.563
- Rank 302 of 659 measured models
- Context window
- 1M
- Rank 84 of 1199 measured models
- Cost per task
- $0.0602
- Rank 39 of 193 measured models
Gemini 3.1 Flash-Lite scores 15.6 on the Artificial Analysis Intelligence Index, ranking 298th of 744 measured models. The closest models on this index are K2 Horizon 3.7B (15.6), Qwen3 Max (15.6), and Claude 4.5 Haiku (15.4). At $0.563 per million tokens (3:1 input/output blended price), it is cheaper than Qwen3 Max ($2.40) and Claude 4.5 Haiku ($2). With an output speed of 342 t/s, it is faster than Qwen3 Max (61.2 t/s) and Claude 4.5 Haiku (87.3 t/s).
Additional benchmarks8
Design Arena · 3d38.8%
Design Arena · Asciiart50.7%
Design Arena · Codecategories36.5%
Design Arena · Dataviz33.3%
Design Arena · Gamedev33.7%
Design Arena · Svg42.5%
Design Arena · Uicomponent37.7%
Design Arena · Website36.6%
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- K2 Horizon 3.7B
Institute of Foundation Models · — · —
15.6——Compare - Qwen3 Max
Alibaba · $2.40 · 61.2 t/s
15.6$2.4061.2 t/sCompare - Claude 4.5 Haiku
Anthropic · $2 · 87.3 t/s
15.4−0.2$287.3 t/sCompare - Claude 3.7 Sonnet
Anthropic · $6 · —
15.3−0.3$6—Compare
