- Intelligence
- 23.7
- Rank 193 of 744 measured models
- Output speed
- 126 t/s
- Rank 125 of 403 measured models
- Price/1M
- $3.44
- Rank 510 of 659 measured models
- Context window
- 400K
- Rank 357 of 1199 measured models
GPT-5.1 Codex (High) scores 23.7 on the Artificial Analysis Intelligence Index, ranking 193rd of 744 measured models. The closest models on this index are MiMo-V2-Omni (23.9), Claude Opus 4.5 (23.7), and GLM 5V Turbo (Reasoning) (23.5). At $3.44 per million tokens (3:1 input/output blended price), it is cheaper than Claude Opus 4.5 ($10). With an output speed of 126 t/s, it is faster than Claude Opus 4.5 (46.1 t/s).
Additional benchmarks8
Design Arena · Codecategories54.6%
Design Arena · Dataviz55.9%
Design Arena · Fullstack44.5%
Design Arena · Gamedev50.5%
Design Arena · Mobileapps53.4%
Design Arena · Uicomponent60.0%
Design Arena · Webapps44.0%
Design Arena · Website56.1%
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- MiMo-V2-Omni
Xiaomi · — · —
23.9+0.2——Compare - Claude Opus 4.5
Anthropic · $10 · 46.1 t/s
23.7$1046.1 t/sCompare - GLM 5V Turbo (Reasoning)
Z.AI · — · —
23.5−0.2——Compare - Kimi K2.5
Moonshot AI · $1.14 · 60.1 t/s
23.5−0.2$1.1460.1 t/sCompare
