# Celeris-1 Benchmark Scores & Performance

> Celeris-1 by Celeris has 17 source-displayable benchmark rows but no public overall score. It remains unranked.

Canonical page: https://benchlm.ai/models/celeris-1

Last updated: September 4, 2026

## Model Details

| Property | Value |
|----------|-------|
| Creator | Celeris |
| Source Type | Proprietary |
| Reasoning Type | Non-Reasoning |
| Context Window | 128K |
| Overall Score | Coming soon |
| Overall Rank | Unranked |

## Family & Coverage

- Family: Celeris-1
- Variant: base
- Benchmarks covered: 17 of 422
- Coverage note: BenchLM currently has partial benchmark coverage for this model, so the overall score is conservative.

## Agentic Benchmarks

| Benchmark | Score |
|-----------|-------|
| [AA Agentic Index](/benchmarks/aaagenticindex) | 2.4% |
| [GDPval-AA](/benchmarks/gdpvalaanormalized) | 1.8% |
| [GDPval-AA](/benchmarks/gdpvalaa) | 536 |

## Coding Benchmarks

| Benchmark | Score |
|-----------|-------|
| [AA Coding Index](/benchmarks/aacodingindex) | 14.4% |
| [AA-SciCode](/benchmarks/aascicode) | 20.7% |

## Reasoning Benchmarks

| Benchmark | Score |
|-----------|-------|
| [AA-LCR](/benchmarks/lcr) | 37.3% |
| [CritPt](/benchmarks/critpt) | 0.0% |
| [DROP](/benchmarks/drop) | 81.4% |

## Knowledge Benchmarks

| Benchmark | Score |
|-----------|-------|
| [MMLU-Pro](/benchmarks/mmlu-pro) | 75.9% |
| [Artificial Analysis Intelligence Index](/benchmarks/artificialanalysis) | 12.3% |
| [AA-GPQA Diamond](/benchmarks/aagpqadiamond) | 63.1% |
| [AA-HLE](/benchmarks/aahle) | 6.8% |
| [AA-Omniscience Index](/benchmarks/aaomniscienceindex) | -71.6% |
| [AA-Omniscience Accuracy](/benchmarks/omniscienceaccuracy) | 11.0% |
| [AA-Omniscience Hallucination Rate](/benchmarks/omnisciencehallucinationrate) | 92.8% |

## Instruction Following Benchmarks

| Benchmark | Score |
|-----------|-------|
| [IFEval](/benchmarks/ifeval) | 80.8% |

## Mathematics Benchmarks

| Benchmark | Score |
|-----------|-------|
| [GSM8K](/benchmarks/gsm8k) | 93.7% |