- Intelligence
- 38.4
- Rank 76 of 744 measured models
- Coding
- 74.9
- Rank 29 of 298 measured models
- Output speed
- 81.9 t/s
- Rank 225 of 403 measured models
- Price/1M
- $11.25
- Rank 630 of 659 measured models
- Context window
- 922K
- Rank 330 of 1199 measured models
- Cost per task
- $2.63
- Rank 172 of 193 measured models
GPT-5.5 (Xhigh) scores 38.4 on the Artificial Analysis Intelligence Index, ranking 76th of 744 measured models. The closest models on this index are Mistral Large 4 Preview (38.4), Claude Sonnet 5 (38.2), and GPT-6 Luna (38.1). At $11.25 per million tokens (3:1 input/output blended price), it is more expensive than Mistral Large 4 Preview ($2.07), Claude Sonnet 5 ($4), and GPT-6 Luna ($0.20). With an output speed of 81.9 t/s, it is faster than Claude Sonnet 5 (74.9 t/s), slower than Mistral Large 4 Preview (116 t/s) and GPT-6 Luna (116 t/s).
Additional benchmarks21
Design Arena · 3d49.4%
Design Arena · Agenticgamedev52.4%
Design Arena · Agentichtmlslides34.2%
Design Arena · Agenticslides Html33.2%
Design Arena · Agenticslides Python Pptx45.2%
Design Arena · Agenticslides43.5%
Design Arena · Androidnative50.9%
Design Arena · Asciiart58.4%
Design Arena · Codecategories53.1%
Design Arena · Dataviz55.7%
Design Arena · Fullstack43.0%
Design Arena · Gamedev57.2%
Design Arena · Godotgamedev52.3%
Design Arena · Htmlslides35.6%
Design Arena · Mobileapps50.4%
Design Arena · Pptxslides45.3%
Design Arena · Python Pptxslides43.3%
Design Arena · Svg55.2%
Design Arena · Uicomponent53.2%
Design Arena · Webapps42.6%
Design Arena · Website52.3%
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- Grok 4.5 (High)
SpaceXSI · $3 · 58.2 t/s
38.8+0.4$358.2 t/sCompare - Mistral Large 4 Preview
Mistral · $2.07 · 116 t/s
38.4$2.07116 t/sCompare - Claude Sonnet 5
Anthropic · $4 · 74.9 t/s
38.2−0.2$474.9 t/sCompare - GPT-6 Luna
OpenAI · $0.20 · 116 t/s
38.1−0.3$0.20116 t/sCompare
