readable AI benchmarks

Celeris

Celeris-1

non-reasoning · closed weights · Jul 24, 2026

Quality Score9.5
Value Score12.0
Reliability14.2
Cache Discountnot available

Model specification

Reasoning
non-reasoning
Input modalities
text, image
Output modalities
text
Context window
131,072 tokens
Weights
closed weights

Token prices USD per 1M tokens

Input
$0.200
Output
$0.700
Cached Input
not available
Cached Output
not available
Cost per task
$0.258

Capability

Intelligence
12.4
Coding
14.4
Agentic
2.4
Omniscience
-71.6
Correct
11.0%
Blended price
$0.250

Answer outcomes

Correct 11.0%Incorrect 82.6%Abstained 6.5%

Artificial Analysis benchmarks

GDPval-AA v2
2%
τ³-Banking
4%
Terminal-Bench v2.1
11%
SciCode
21%
Humanity’s Last Exam
7%
GPQA Diamond
63%
CritPt
0%
AA-Omniscience
14%
AA-LCR
37%

Similar models