# Celeris-1 Decision Benchmark Scores & Performance

> Celeris reports 80.0% accuracy on 22 jev-bench datasets totaling 3,210 items and 76.5% on 400 typed-decisions cases with five questions each. The table preserves its October 2026 comparison, run through each provider’s decision endpoint with one scorer. Lower Brier scores mean smaller errors in the reported probabilities.

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

Last updated: 2026-10-08

General benchmark catalog last updated: October 9, 2026. This profile’s source review has its own date above.

## Model Details

| Property | Value |
|----------|-------|
| Creator | Celeris |
| Source Type | Proprietary |
| Reasoning Type | Unspecified |
| Context Window | Not published for this endpoint |
| Official model card | [Celeris Decision API documentation](https://docs.celeris.ai/decisions) |
| Overall Score | Not computed (provider decision report only) |
| Overall Rank | Unranked |

## Family & Coverage

- Family: Celeris-1 Decision
- Variant: decision-system
- Benchmarks covered: 0 of 625
- Coverage note: The provider decision report appears below; no general benchmark scores are inherited.

## Decision API and pricing

Celeris released Celeris-1 Decision on October 8, 2026, as a hosted diffusion model for Noul, Choice, and Score questions. It accepts text, JSON, and images through a System One-compatible API, with optional one-sentence explanations. Celeris lists $0.04 per million input tokens, including cached input, and free output. Reported input usage includes the internal request representation and images.

## Provider-reported decision results

These are provider-reported results from decision-benching harness 0cfd276. This jev-bench accuracy is separate from the official JevBench composite and Perplexity’s 11-task panel. The two Brier scores use different gold labels: hard labels for jev-bench and soft distributions for typed decisions. Failed requests or missing distributions were scored as uniform. Latency was measured end to end from AWS us-east-1; optional explanations add latency. We have not rerun this evaluation, and these results stay outside general model rankings.

| Metric | Celeris-1 Decision |
| --- | --- |
| jev-bench accuracy · 3,210 items | 80.0% |
| jev-bench Brier · lower is better | 0.272 |
| Typed-decisions accuracy · 400 × 5 questions | 76.5% |
| Typed-decisions Brier · lower is better | 0.079 |
| Median response · 1 question | 67 ms |
| Median response · 50 questions | 81 ms |

[Full decision-model comparison](/decision-models#celeris) · [Launch and methodology](https://celeris.ai/celeris-1-decision) · [API documentation](https://docs.celeris.ai/decisions) · [Official pricing](https://docs.celeris.ai/pricing)

## Other Celeris Models

- [Celeris-1](/models/celeris-1) - Score: 28.67