Skip to content

Celeris-1

CelerisProprietaryNon-reasoningProvisionalReleased Jul 22, 2026
Compare with Claude 3 OpusSource scores ↗
Overall score
28.4
Rank 194 of 222 · 14.1–42.8
Context window
128K
128,000 tokens
Price per 1M tokens
$0.20 in · $0.70 out
Source: BenchLM
Blended price
$0.33
3:1 input:output tokens
Output speed
—
Not measured yet

Category scores

Scores per capability area with the model's rank among ranked models in that category.

  1. 1Knowledge61.5
  2. 2Reasoning51.1
Higher is better. #N is the model's rank in that category, where it is eligible to be ranked.

Benchmark results (4)

As reported in system cards, papers and public evaluations. Position compares this model with every other model reporting the same benchmark.

Reasoning

DROP81.4#4 of 5

Knowledge

MMLU-Pro75.9#43 of 67

Instruction following

IFEval80.8#43 of 53

Math

GSM8K93.7#3 of 6

Pricing by source

USD per 1M tokens.

SourceInputOutputCached in
List price (BenchLM)$0.20$0.70—

Celeris's official pricing guide lists $0.20 per million prompt tokens and $0.70 per million completion tokens. The official model guide lists a 131,072-token combined prompt and requested-output limit.

Speed

Measured by us through OpenRouter (median of trials).

Not available on OpenRouter, so we cannot measure it yet.

Related models

Similar score