# Ember-1 Benchmark Scores & Performance

> Ember-1 by Fireworks has 5 source-displayable benchmark rows but no public overall score. It remains unranked.

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

Last updated: September 28, 2026

## Model Details

| Property | Value |
|----------|-------|
| Creator | Fireworks |
| Source Type | Proprietary |
| Reasoning Type | Reasoning |
| Context Window | 1.04M |
| Official model card | [Fireworks Ember-1 model page](https://fireworks.ai/models/fireworks/ember-1) |
| Overall Score | Coming soon |
| Overall Rank | Unranked |

## Family & Coverage

- Family: Fireworks Ember
- Variant: base (Research Preview)
- Benchmarks covered: 5 of 486
- Coverage note: BenchLM currently has partial benchmark coverage for this model, so the overall score is conservative.

## Agentic Benchmarks

| Benchmark | Score |
|-----------|-------|
| [Terminal-Bench 2.1](/benchmarks/terminalbench21) | 82.0% |
| [τ²-bench Airline](/benchmarks/tau2airline) | 66.0% |

## Coding Benchmarks

| Benchmark | Score |
|-----------|-------|
| [Terminal-Bench 2.1](/benchmarks/terminalbench21) | 82.0% |
| [SWE-bench Verified](/benchmarks/swe-bench-verified) | 92.2% |
| [DeepSWE](/benchmarks/deepswe) | 75.2% |