readable AI benchmarks (simplified)

readable AI benchmarks

OpenAI

GPT-5.4 mini (Non-Reasoning)

non-reasoning · closed weights · Mar 17, 2026

GPT-5.4 mini (Non-Reasoning) has a Quality Score of 22.2, ranking 342nd among 551 scored models. Per 1M tokens, pricing is $0.750 input, $4.50 output, and $0.075 cached input. It has a 400k token context window. Its Reliability Score is 27.3, ranking 341st among 553 scored models, below average (total average: 35.6). Its Value Score is 16.4, low compared with the total Value average of 30.7.

Quality Score22.2coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score16.4
Factual reliability27.3
Cache Discount90%

Model specification

Reasoning
non-reasoning
Input modalities
none
Output modalities
none
Context window
400k tokens
Weights
closed weights

Token prices USD per 1M tokens

Input
$0.750
Output
$4.50
Cached Input
$0.075
Cache write
not available
Cost per task
not available

Capability

Intelligence
11.1
Coding
not available
Agentic
not available
Omniscience
-45.4
Correct
25.7%
Blended price
$0.653

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 96.7%

Correct 25.7%Incorrect 71.1%Partial / not attempted 3.3%

Artificial Analysis benchmarks

GDPval-AA v2
4%
Humanity’s Last Exam
6%
GPQA Diamond
61%
CritPt
0%
AA-Omniscience
27%
AA-LCR
37%

Similar models

Support me! Patreon