- Intelligence
- 23.0
- Rank 201 of 744 measured models
- Coding
- 37.8
- Rank 161 of 298 measured models
- Output speed
- 102 t/s
- Rank 164 of 403 measured models
- Price/1M
- $3.44
- Rank 510 of 659 measured models
- Context window
- 400K
- Rank 357 of 1199 measured models
GPT-5 (High) scores 23.0 on the Artificial Analysis Intelligence Index, ranking 201st of 744 measured models. The closest models on this index are GPT-5 (batch) (23.0), Nemotron 3 Ultra 550B A55B (22.9), and Qwen3.5 27B (22.9). At $3.44 per million tokens (3:1 input/output blended price), it is more expensive than GPT-5 (batch) ($1.72), Nemotron 3 Ultra 550B A55B ($1.08), and Qwen3.5 27B ($0.825). With an output speed of 102 t/s, it is faster than Qwen3.5 27B (76.5 t/s), slower than Nemotron 3 Ultra 550B A55B (155 t/s).
Additional benchmarks8
Design Arena · 3d41.3%
Design Arena · Asciiart49.0%
Design Arena · Codecategories54.5%
Design Arena · Dataviz60.5%
Design Arena · Gamedev59.3%
Design Arena · Svg64.1%
Design Arena · Uicomponent57.4%
Design Arena · Website53.7%
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- GPT-5 (batch)
OpenAI · $1.72 · —
23.0$1.72—Compare - Nemotron 3 Ultra 550B A55B
NVIDIA · $1.08 · 155 t/s
22.9−0.1$1.08155 t/sCompare - Qwen3.5 27B
Alibaba · $0.825 · 76.5 t/s
22.9−0.1$0.82576.5 t/sCompare - MiniMax-M2.5
MiniMax · $0.525 · 66.5 t/s
22.8−0.2$0.52566.5 t/sCompare
