- Intelligence
- 32.5
- Rank 112 of 744 measured models
- Output speed
- 98.5 t/s
- Rank 171 of 403 measured models
- Price/1M
- $4.81
- Rank 574 of 659 measured models
- Context window
- 400K
- Rank 357 of 1199 measured models
GPT-5.3 Codex (Xhigh) scores 32.5 on the Artificial Analysis Intelligence Index, ranking 112th of 744 measured models. The closest models on this index are Gemini 3.5 Flash (32.6), Motif 3 (Beta) (32.3), and Claude Opus 4.6 (batch) (31.9). At $4.81 per million tokens (3:1 input/output blended price), it is more expensive than Gemini 3.5 Flash ($3.38). With an output speed of 98.5 t/s, it is slower than Gemini 3.5 Flash (177 t/s).
Additional benchmarks13
Design Arena · 3d35.3%
Design Arena · Androidnative35.2%
Design Arena · Asciiart51.2%
Design Arena · Codecategories47.2%
Design Arena · Dataviz50.6%
Design Arena · Fullstack36.5%
Design Arena · Gamedev51.3%
Design Arena · Godotgamedev45.1%
Design Arena · Mobileapps41.4%
Design Arena · Svg54.0%
Design Arena · Uicomponent47.3%
Design Arena · Webapps36.9%
Design Arena · Website48.6%
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- Motif 3
Motif Technologies · — · —
33.6+1.1——Compare - Gemini 3.5 Flash
Google · $3.38 · 177 t/s
32.6+0.1$3.38177 t/sCompare - Motif 3 (Beta)
Motif Technologies · — · —
32.3−0.2——Compare - Claude Opus 4.6 (batch)
Anthropic · — · —
31.9−0.6——Compare
