readable AI benchmarks

OpenAI

GPT-5.3 Codex (xhigh)

reasoning · closed weights · Feb 5, 2026

Quality Score58.6
Value Score39.0
Reliability55.4
Cache Discount90%

Model specification

Reasoning
reasoning
Input modalities
text, image
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
Cached Output
not available
Cost per task
not available

Capability

Intelligence
45.5
Coding
not available
Agentic
not available
Omniscience
10.9
Correct
52.9%
Blended price
$1.87

Answer outcomes

Correct 52.9%Incorrect 42.0%Abstained 5.1%

Artificial Analysis benchmarks

SciCode
53%
Humanity’s Last Exam
42%
GPQA Diamond
92%
CritPt
17%
AA-Omniscience
55%
AA-LCR
78%

Similar models