readable AI benchmarks (simplified)

readable AI benchmarks

OpenAI

GPT-4o (Aug '24)

non-reasoning · closed weights · Aug 6, 2024

GPT-4o (Aug '24) has a Quality Score of 25.7, ranking 298th among 551 scored models. Per 1M tokens, pricing is $2.50 input, $10.00 output, and $1.25 cached input. It accepts text and image input, outputs text, and has a 128k token context window. Its Reliability Score is 39.6, ranking 221st among 553 scored models, above average (total average: 35.6). Its Value Score is 16.2, low compared with the total Value average of 30.7.

Quality Score25.7coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score16.2
Factual reliability39.6
Cache Discount50%

Model specification

Reasoning
non-reasoning
Input modalities
text, image
Output modalities
text
Context window
128k tokens
Weights
closed weights

Token prices USD per 1M tokens

Input
$2.50
Output
$10.00
Cached Input
$1.25
Cache write
not available
Cost per task
not available

Capability

Intelligence
7.7
Coding
not available
Agentic
not available
Omniscience
-20.9
Correct
23.7%
Blended price
$2.38

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 68.3%

Correct 23.7%Incorrect 44.6%Partial / not attempted 31.7%

Artificial Analysis benchmarks

Humanity’s Last Exam
2%
GPQA Diamond
52%
CritPt
0%
AA-Omniscience
40%
AA-LCR
41%

Similar models

Support me! Patreon