OpenAI
GPT-4.1 Nano (batch)
- Intelligence
- 7.8
- Rank 527 of 768 measured models
- Coding
- 11.1
- Rank 264 of 299 measured models
- Web Search
- $10 /1K calls
- Context window
- 1.05M
- Rank 84 of 1296 measured models
GPT-4.1 Nano (batch) scores 7.8 on the Artificial Analysis Intelligence Index, ranking 527th of 768 measured models. The closest models on this index are DeepSeek R1 Distill Qwen 14B (7.8), Falcon-H1R-7B (7.8), and Gemma 4 E2B (7.8).
Additional benchmarks6
Design Arena · 3d46.0%
Design Arena · Codecategories47.3%
Design Arena · Dataviz41.1%
Design Arena · Gamedev49.6%
Design Arena · Uicomponent43.9%
Design Arena · Website48.1%
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- DeepSeek R1 Distill Qwen 14B
DeepSeek · — · —
7.8——Compare - Falcon-H1R-7B
TII · — · —
7.8——Compare - Gemma 4 E2B
Google · — · —
7.8——Compare - GPT-4.1 nano
OpenAI · $0.175 · 223 t/s
7.8$0.175223 t/sCompare
