readable AI benchmarks (simplified)

readable AI benchmarks

OpenAI

GPT-5.4 nano (medium)

reasoning · closed weights · Mar 17, 2026

GPT-5.4 nano (medium) has a Quality Score of 35.9, ranking 208th among 551 scored models. Per 1M tokens, pricing is $0.200 input, $1.25 output, and $0.020 cached input. It has a 400k token context window. Its Reliability Score is 41.0, ranking 211th among 553 scored models, above average (total average: 35.6). Its Value Score is 30.6, around average compared with the total Value average of 30.7.

Quality Score35.9coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score30.6
Factual reliability41.0
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
$0.200
Output
$1.25
Cached Input
$0.020
Cache write
not available
Cost per task
not available

Capability

Intelligence
20.0
Coding
not available
Agentic
not available
Omniscience
-18.0
Correct
21.9%
Blended price
$0.179

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 61.8%

Correct 21.9%Incorrect 39.9%Partial / not attempted 38.2%

Artificial Analysis benchmarks

Humanity’s Last Exam
16%
GPQA Diamond
76%
CritPt
5%
AA-Omniscience
41%
AA-LCR
67%

Similar models

Support me! Patreon