readable AI benchmarks

OpenAI

GPT-5.5 Instant (June 2026)

reasoning · closed weights · Jun 25, 2026

Quality Score44.5
Value Score24.8
Reliability51.9
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
$5.00
Output
$30.00
Cached Input
$0.500
Cached Output
not available
Cost per task
$0.536

Capability

Intelligence
29.2
Coding
39.4
Agentic
11.1
Omniscience
3.7
Correct
44.4%
Blended price
$4.35

Answer outcomes

Correct 44.4%Incorrect 40.7%Abstained 14.9%

Artificial Analysis benchmarks

GDPval-AA v2
11%
τ³-Banking
12%
Terminal-Bench v2.1
35%
SciCode
49%
Humanity’s Last Exam
20%
GPQA Diamond
82%
CritPt
0%
AA-Omniscience
52%
AA-LCR
67%

Similar models