- Intelligence
- 13.0
- Rank 348 of 744 measured models
- Output speed
- 159 t/s
- Rank 73 of 403 measured models
- Price/1M
- $0.138
- Rank 122 of 659 measured models
- Context window
- 400K
- Rank 357 of 1199 measured models
GPT-5 nano (High) scores 13.0 on the Artificial Analysis Intelligence Index, ranking 348th of 744 measured models. The closest models on this index are DeepSeek R1 0528 (May '25) (13.1), Qwen3.5 4B (13.1), and GPT-5 Nano (batch) (13.0). At $0.138 per million tokens (3:1 input/output blended price), it is cheaper than DeepSeek R1 0528 (May '25) ($1.76), more expensive than Qwen3.5 4B ($0.060) and GPT-5 Nano (batch) ($0.0687). With an output speed of 159 t/s, it is faster than DeepSeek R1 0528 (May '25) (31.9 t/s) and Qwen3.5 4B (19.9 t/s).
Additional benchmarks6
Design Arena · 3d36.3%
Design Arena · Codecategories48.0%
Design Arena · Dataviz46.2%
Design Arena · Gamedev46.5%
Design Arena · Uicomponent51.9%
Design Arena · Website48.9%
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- DeepSeek R1 0528 (May '25)
DeepSeek · $1.76 · 31.9 t/s
13.1+0.1$1.7631.9 t/sCompare - Qwen3.5 4B
Alibaba · $0.060 · 19.9 t/s
13.1+0.1$0.06019.9 t/sCompare - GPT-5 Nano (batch)
OpenAI · $0.0687 · —
13.0$0.0687—Compare - Nemotron 3.5 Lightning
NVIDIA · $0.095 · 302 t/s
12.9−0.1$0.095302 t/sCompare
