readable AI benchmarks (simplified)

readable AI benchmarks

OpenAI

GPT-5.4 (Non-reasoning)

non-reasoning · closed weights · Mar 5, 2026

GPT-5.4 (Non-reasoning) has a Quality Score of 35.1, ranking 211th among 551 scored models. Per 1M tokens, pricing is $2.50 input, $15.00 output, and $0.250 cached input. It has a 1050k token context window. Its Reliability Score is 42.2, ranking 197th among 553 scored models, above average (total average: 35.6). Its Value Score is 22.3, low compared with the total Value average of 30.7.

Quality Score35.1coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score22.3
Factual reliability42.2
Cache Discount90%

Model specification

Reasoning
non-reasoning
Input modalities
none
Output modalities
none
Context window
1050k tokens
Weights
closed weights

Token prices USD per 1M tokens

Input
$2.50
Output
$15.00
Cached Input
$0.250
Cache write
not available
Cost per task
not available

Capability

Intelligence
18.2
Coding
not available
Agentic
not available
Omniscience
-15.7
Correct
37.4%
Blended price
$2.18

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 90.4%

Correct 37.4%Incorrect 53.0%Partial / not attempted 9.6%

Artificial Analysis benchmarks

Humanity’s Last Exam
11%
GPQA Diamond
75%
CritPt
1%
AA-Omniscience
42%
AA-LCR
58%

Similar models

Support me! Patreon