readable AI benchmarks (simplified)

readable AI benchmarks

OpenAI

GPT-5 nano (high)

reasoning · closed weights · Aug 7, 2025

GPT-5 nano (high) has a Quality Score of 27.8, ranking 275th among 551 scored models. Per 1M tokens, pricing is $0.050 input, $0.400 output, and $0.0050 cached input. It accepts text and image input, outputs text, and has a 400k token context window. Its Reliability Score is 35.7, ranking 253rd among 553 scored models, above average (total average: 35.6). Its Value Score is 26.0, low compared with the total Value average of 30.7.

Quality Score27.8coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score26.0
Factual reliability35.7
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
$0.050
Output
$0.400
Cached Input
$0.0050
Cache write
not available
Cost per task
not available

Capability

Intelligence
13.0
Coding
not available
Agentic
not available
Omniscience
-28.7
Correct
19.1%
Blended price
$0.054

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 66.8%

Correct 19.1%Incorrect 47.8%Partial / not attempted 33.2%

Artificial Analysis benchmarks

Humanity’s Last Exam
9%
GPQA Diamond
68%
CritPt
0%
AA-Omniscience
36%
AA-LCR
45%

Similar models

Support me! Patreon