Advertise here
#297

Ember-1

Fireworks Release: 2026-09-28 Tested on: 2026-09-28 08:11 fireworks/ember-1::none
~2.8T total (~104B active)MoEClosedEstimated
(max) (high) (low) (none)

Summary

Ember-1 scores 5.2 on AI BENCHY and ranks #297. It has 8.1 reliability, a 42.4% pass rate, $0.123 total cost, and 19.46s average response time.

What makes Ember-1 unique: It stands out most in Puzzle Solving, where it ranks #1, while Data parsing and extraction is its weakest area at #15.

Model facts

Researched on 2026-09-28

Estimated
Parameters
~2.8T total (~104B active)
Architecture
MoE
Availability
Closed
License
-

Best estimate from public evidence; the vendor did not disclose every value. Fireworks reports post-training on Kimi K3 for shorter reasoning. Architecture and parameter estimates inherit Kimi K3's reported 2.8T total and 104B active parameters; Ember-specific counts are not disclosed. The exact Ember checkpoint is offered as a serverless research preview, with no public weights identified.

Parameter source 1 Parameter source 2 Availability source

Score

5.2

Consistency

8.9

Reliability

8.1

Total Cost (Current Price)

$0.123

Total Output Tokens

2,664

Total Input Tokens

27,426

Input Price

$3.000 / 1M

Output Price

$15.000 / 1M

Tests Correct

Wrong Tests: 14

Attempt pass rate: 42.4%

Flaky tests

3

Flaky tests had mixed outcomes across runs (at least one pass and one fail).

Response Time (avg)

19.46s

Response Time (max): 93.12s

Response Time (total): 428.04s

Wrong answer: 9 API error: 5

Hamster playing table tennis

Prompt: Create a detailed SVG illustration of a hamster playing table tennis.

#297 Ember-1

none
Cost
$0.156
Time
224.6s
Tokens
10,555 tok

Charts

Choose the first model, then click a second model to open a side-by-side page.

Total Output Tokens

Score vs Total Output Tokens

Quick Compare

Ember-1nonevsInklingnoneEmber-1nonevsGranite 4.2 8BmediumEmber-1nonevsDots 3 Note PreviewnoneFree AvailableEmber-1nonevsNemotron 3.5 LightningmediumFree AvailableEmber-1nonevsQwen3.6 35B A3BnoneEmber-1nonevsMistral Small 4noneEmber-1nonevsLing-2.6-1TnoneEmber-1nonevsMistral Small 4mediumEmber-1nonevsSeed-2.0-CodenoneEmber-1nonevsGranite 4.2 8Blow

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 5.2 7.9
Coding 5.5 10.0
Combined 3.0 10.0
Data parsing and extraction 6.4 5.9
Domain specific 5.3 10.0
General Intelligence 5.0 10.0
Instructions following 6.4 5.8
Puzzle Solving 10.0 10.0
Tool Calling 3.0 10.0
Trivia 3.0 10.0

Compared models