Back

OpenAI

GPT-5.2

ReasoningClosed weights
Intelligence
26.5
Rank 157 of 744 measured models
Price/1M
$4.81
Rank 574 of 659 measured models
Context window
400K
Rank 357 of 1199 measured models

GPT-5.2 (Medium) scores 26.5 on the Artificial Analysis Intelligence Index, ranking 157th of 744 measured models. The closest models on this index are GLM-5-Turbo (26.6), Apodex 1.1 (26.4), and Claude Opus 4.6 (26.4). At $4.81 per million tokens (3:1 input/output blended price), it is cheaper than Claude Opus 4.6 ($10), more expensive than Apodex 1.1 ($0.975).

Artificial Analysis Indices
Medium
Intelligence26.5
Rank 157 of 744 measured models
Math96.7
Rank 4 of 270 measured models
Reasoning levels
Each point is a reasoning level of this model: more reasoning often raises the score but costs more. Select a point to open that level.
Intelligence Indexmost efficient ↗Price / 1M tokens
Standard Benchmarks
MMLU Pro85.9%
Rank 24 of 349 measured models
GPQA Diamond86.4%
Rank 118 of 619 measured models
HLE26.7%
Rank 180 of 664 measured models
LiveCodeBench89.4%
Rank 4 of 343 measured models
AIME 202596.7%
Rank 4 of 270 measured models
IFBench65.2%
Rank 104 of 450 measured models
AA-LCR70.3%
Rank 214 of 575 measured models
TerminalBench Hard43.2%
Rank 41 of 432 measured models
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.

Preferences and analytics

Rybbit: visits, performance, clicks, copies, forms and session replay (masked inputs), with your permission. Refusing does not limit the site.

Privacy

Allow navigation analytics?

With your permission, Rybbit measures visits, performance and interactions (clicks, copies, forms), including session replay, to improve BenchSift. Input values are masked in replays. Refusing does not limit the site.

Your choice is stored for 180 days. Change it at any time using “Privacy preferences” in the footer. Withdrawal reloads the page.

No choice stored: Rybbit is disabled.

Privacy