readable AI benchmarks (simplified)

readable AI benchmarks

OpenAI

GPT-5.2 Codex (xhigh)

reasoning · closed weights · Dec 11, 2025

GPT-5.2 Codex (xhigh) has a Quality Score of 46.4, ranking 121st among 551 scored models. Per 1M tokens, pricing is $1.75 input, $14.00 output, and $0.175 cached input. It accepts text, image, and pdf input, outputs text, and has a 400k token context window. Its Reliability Score is 48.9, ranking 126th among 553 scored models, above average (total average: 35.6). Its Value Score is 30.1, around average compared with the total Value average of 30.7.

Quality Score46.4coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score30.1
Factual reliability48.9
Cache Discount90%

Model specification

Reasoning
reasoning
Input modalities
text, image, pdf
Output modalities
text
Context window
400k tokens
Weights
closed weights

Token prices USD per 1M tokens

Input
$1.75
Output
$14.00
Cached Input
$0.175
Cache write
not available
Cost per task
not available

Capability

Intelligence
28.5
Coding
not available
Agentic
not available
Omniscience
-2.2
Correct
41.1%
Blended price
$1.87

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 84.3%

Correct 41.1%Incorrect 43.2%Partial / not attempted 15.7%

Artificial Analysis benchmarks

Humanity’s Last Exam
36%
GPQA Diamond
90%
CritPt
9%
AA-Omniscience
49%
AA-LCR
82%

Similar models

Support me! Patreon