readable AI benchmarks (simplified)

readable AI benchmarks

OpenAI

GPT-5 (medium)

reasoning · closed weights · Aug 7, 2025

GPT-5 (medium) has a Quality Score of 39.9, ranking 172nd among 551 scored models. Per 1M tokens, pricing is $1.25 input, $10.00 output, and $0.125 cached input. It has a 400k token context window. Its Reliability Score is 44.6, ranking 177th among 553 scored models, above average (total average: 35.6). Its Value Score is 26.9, around average compared with the total Value average of 30.7.

Quality Score39.9coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score26.9
Factual reliability44.6
Cache Discount90%

Model specification

Reasoning
reasoning
Input modalities
none
Output modalities
none
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
22.9
Coding
not available
Agentic
not available
Omniscience
-10.9
Correct
39.5%
Blended price
$1.34

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 89.8%

Correct 39.5%Incorrect 50.3%Partial / not attempted 10.2%

Artificial Analysis benchmarks

Humanity’s Last Exam
25%
GPQA Diamond
84%
CritPt
0%
AA-Omniscience
45%
AA-LCR
76%

Similar models

Support me! Patreon