readable AI benchmarks (simplified)
Z AI
Celeris
Celeris has a Quality Score of 14.5, ranking 220th among 238 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 224th among 245 scored models, below average (total average: 46.4). Its Value Score is 11.4, low compared with the total Value average of 28.3.
Quality Score14.5coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score11.4
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
- Omniscience (native net)
- -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 legacy records
- Humanity’s Last Exam
- 3%
- GPQA Diamond
- 57%
- CritPt
- 0%
- AA-LCR
- 0%
Similar models
- Public AIZ AIQuality Score 14.5Value Score 11.4
- ReplicateZ AIQuality Score 14.5Value Score 11.4
- GLM-4.7-Flash (Non-reasoning)Z AIQuality Score 13.0Value Score 11.9
- GLM-4.7 (Non-reasoning)Z AIQuality Score 21.8Value Score 16.1
- GLM-4.5V (Reasoning)Z AIQuality Score 17.2Value Score 13.5
- GLM-5 (Non-reasoning)Z AIQuality Score 32.9Value Score 24.2