readable AI benchmarks (simplified)

readable AI benchmarks

OpenAI

GPT-5.5 (high)

reasoning · closed weights · Apr 23, 2026

GPT-5.5 (high) has a Quality Score of 66.0, ranking 13th among 53 scored models. Per 1M tokens, pricing is $5.00 input, $30.00 output, and $0.500 cached input. Its Reliability Score is 59.2, ranking 15th among 53 scored models, above average (total average: 50.1). Its Value Score is 40.3, around average compared with the total Value average of 39.6.

Quality Score66.0coverage 93.8%: missing Epoch General ECI and DeepSWE v1.1
Value Score40.3
Reliability59.2
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
$0.668

Capability

Intelligence
53.1
Coding
71.6
Agentic
43.5
Omniscience
18.4
Correct
56.0%
Blended price
$4.35

Answer outcomes

Attempt rate: 93.7%

Correct 56.0%Incorrect 37.7%Abstained 6.3%

Artificial Analysis benchmarks

GDPval-AA v2
48%
τ³-Banking
29%
Terminal-Bench v2.1
79%
SciCode
56%
Humanity’s Last Exam
43%
GPQA Diamond
93%
CritPt
25%
AA-Omniscience
59%
AA-LCR
73%

Similar models