readable AI benchmarks (simplified)

readable AI benchmarks

Z AI

Celeris

non-reasoning · open weights · release date not listed

Celeris has a Quality Score of 16.3, ranking 458th among 551 scored models. Per 1M tokens, pricing is $0.600 input, $1.80 output, and $0.110 cached input. It has a 64k token context window. Its Reliability Score is 22.2, ranking 428th among 553 scored models, below average (total average: 35.6). Its Value Score is 12.8, low compared with the total Value average of 30.7.

Quality Score16.3coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score12.8
Factual reliability22.2
Cache Discount82%

Model specification

Reasoning
non-reasoning
Input modalities
none
Output modalities
none
Context window
64k tokens
Weights
open weights

Token prices USD per 1M tokens

Input
$0.600
Output
$1.80
Cached Input
$0.110
Cache write
not available
Cost per task
not available

Capability

Intelligence
6.7
Coding
not available
Agentic
not available
Omniscience
-55.6
Correct
18.2%
Blended price
$0.377

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 92.0%

Correct 18.2%Incorrect 73.8%Partial / not attempted 8.0%

Artificial Analysis benchmarks

Humanity’s Last Exam
3%
GPQA Diamond
57%
CritPt
0%
AA-Omniscience
22%
AA-LCR
0%

Similar models

Support me! Patreon