NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-13-01M4TAJNCYDZ9CDMKF0NN8VNSX
Run Details
Model:
Ember-1 (Reasoning, Max)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
2m 1s
Cost:
$0.096122
Provider:
Fireworks
Evaluation summary
Score
Evaluator
Details Link
99.74%
Matches word count
(details)
99.96%
Dialogue to Total Word Ratio
(details)
99.8505%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% words of dialogue between two thieves named Molly and Bill who are planning to break into a children's party to steal all the presents. Only include the prose of the scene without any markdown or commentary.
Model response
Messages
Meta
AI
Molly unrolled the blueprint across the hood of the getaway minivan, smoothing out the crayon lines with one gloved hand. Bill squinted at it, hands shoved deep in his pockets. "Why does the floor plan have a balloon animal on it?" "That's the bouncy castle. The stick figure is Timmy. Six years old. Ruthless." Bill scratched his chin and leaned closer. "Remind me why we're robbing a child?" "Rich grandmother. The kid's getting a solid gold yo-yo worth eight grand." Bill whistled through his teeth. Molly traced the route with her finger. "We go in as clowns. You juggle, I handle the piƱata." "I can't juggle." "You can't do anything, Bill. Never stopped us before." Molly tapped a red X in the corner of the map. "The presents are guarded by the most dangerous security system known to man." "Which is?" "A dozen sugared-up six-year-olds and one very tired magician." Bill gulped audibly and tugged at his collar, staring at the crayon map for a long moment, weighing every life choice that had led him to this minivan. "I'm going to need a bigger bag." "Now you're thinking like a professional," Molly said, rolling up the blueprint and tossing him a red foam nose.
created_at
"2026-10-13T09:47:55.176Z"
10/13/2026, 9:47:55 AM
model
"fireworks/ember-1-20260923"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
391
moderation_latency
(null)
generation_time
121301
tokens_prompt
75
tokens_completion
5566
native_tokens_prompt
149
native_tokens_completion
6405
native_tokens_completion_images
(null)
native_tokens_reasoning
5566
native_tokens_cached
148
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
num_fetches
(null)
web_search_engine
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
service_tier
(null)
usage
0.0961224
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791884875-Kc7OLNl90vczuD8aGYbp"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791884875-xmKfHyz0Kg1jiCoThFip"
upstream_id
"chatcmpl-1c63ad570f114264b761ded714705b79"
provider_responses
0
endpoint_id
"b89a2f05-4051-4446-a9b0-7bc8ae7b7c90"
id
"chatcmpl-1c63ad570f114264b761ded714705b79"
is_byok
false
latency
391
model_permaslug
"fireworks/ember-1-20260923"
provider_name
"Fireworks"
status
200
total_cost
0.0961224
cache_discount
0.0003996
upstream_inference_cost
0
provider_name
"Fireworks"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
99.74%
Matches word count
n/a
neededClean
false
words
204
99.96%
Dialogue to Total Word Ratio
Ratio: 51.44%, Deviation: 1.44%
neededClean
false
wordsTotal
208
wordsDialogue
107
99.8505%