readable AI benchmarks (simplified)

readable AI benchmarks

OpenAI

GPT-5.5 (xhigh)

reasoning · closed weights · Apr 23, 2026

GPT-5.5 (xhigh) has a Quality Score of 67.6, ranking 10th among 53 scored models. Per 1M tokens, pricing is $5.00 input, $30.00 output, and $0.500 cached input. Its Reliability Score is 60.0, ranking 10th among 53 scored models, above average (total average: 50.1). Its Value Score is 41.5, around average compared with the total Value average of 39.6.

Quality Score67.6coverage 93.8%: missing Epoch General ECI and DeepSWE v1.1
Value Score41.5
Reliability60.0
Cache Discount90%

Model specification

Reasoning
reasoning
Input modalities
none
Output modalities
none
Context window
not available
Weights
closed weights

Token prices USD per 1M tokens

Input
$5.00
Output
$30.00
Cached Input
$0.500
Cache write
not available
Cost per task
$0.992

Capability

Intelligence
54.8
Coding
74.9
Agentic
44.9
Omniscience
20.1
Correct
56.9%
Blended price
$4.35

Answer outcomes

Attempt rate: 93.8%

Correct 56.9%Incorrect 36.9%Abstained 6.2%

Artificial Analysis benchmarks

GDPval-AA v2
50%
τ³-Banking
31%
Terminal-Bench v2.1
84%
SciCode
56%
Humanity’s Last Exam
44%
GPQA Diamond
94%
CritPt
27%
AA-Omniscience
60%
AA-LCR
74%

Similar models