readable AI benchmarks (simplified)

readable AI benchmarks

OpenAI

GPT-5 (high)

reasoning · closed weights · Aug 7, 2025

GPT-5 (high) has a Quality Score of 40.5, ranking 169th among 551 scored models. Per 1M tokens, pricing is $1.25 input, $10.00 output, and $0.125 cached input. It accepts text and image input, outputs text, and has a 400k token context window. Its Reliability Score is 45.6, ranking 156th among 553 scored models, above average (total average: 35.6). Its Value Score is 27.3, around average compared with the total Value average of 30.7.

Quality Score40.5coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score27.3
Factual reliability45.6
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
$1.25
Output
$10.00
Cached Input
$0.125
Cache write
not available
Cost per task
not available

Capability

Intelligence
23.0
Coding
not available
Agentic
not available
Omniscience
-8.7
Correct
40.3%
Blended price
$1.34

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 89.4%

Correct 40.3%Incorrect 49.0%Partial / not attempted 10.6%

Artificial Analysis benchmarks

GDPval-AA v2
20%
τ³-Banking
22%
Humanity’s Last Exam
28%
GPQA Diamond
85%
CritPt
6%
AA-Omniscience
46%
AA-LCR
78%

Similar models

Support me! Patreon