NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-13-01M4TP79FKZCJ6F781ZV8EK2G4
Run Details
Model:
Ember-1 (Reasoning, Max)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
33.4s
Cost:
$0.038952
Provider:
Fireworks
Evaluation summary
Score
Evaluator
Details Link
27.17%
Matches word count
(details)
99.96%
Dialogue to Total Word Ratio
(details)
63.5636%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 spread the blueprints across the hood of the van, weighting the corners with a juice box and a half-eaten dinosaur nugget. The Henderson birthday party was Fort Knox with streamers, and she had studied it the way other thieves studied casinos, which is to say with a magnifying glass and an unhealthy amount of coffee. "Ball pit here," she said, tapping the diagram. "That's our entry point." Bill squinted. He had spent three days undercover as a balloon animal artist, and the trauma showed in his hands, which now twisted everything he touched into crude dachshunds. The guest list ran forty names deep, every one of them under four feet tall, every one of them armed with cake. "The piƱata's a decoy," Bill whispered. Molly nodded grimly. The real haul was the present table, thirty gift-wrapped boxes, unguarded during the musical chairs window, which her intelligence suggested lasted exactly four minutes and twelve seconds. She had bribed the clown for the seating chart. She had memorized the escape route past the bounce house. She had even procured two tiny party hats as disguises, though Bill's kept sliding off his enormous head, and the chin strap was starting to chafe. "We go in at two," Molly said, folding the map. "Nobody gets hugged." Bill saluted with a balloon poodle.
created_at
"2026-10-13T13:11:25.59Z"
10/13/2026, 1:11:25 PM
model
"fireworks/ember-1-20260923"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1949
moderation_latency
(null)
generation_time
33177
tokens_prompt
75
tokens_completion
2276
native_tokens_prompt
149
native_tokens_completion
2567
native_tokens_completion_images
(null)
native_tokens_reasoning
2266
native_tokens_cached
0
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
0.038952
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791897085-pkcZujx2uRnSBisaeAqt"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791897085-18K2fCajBzLkpTr4K3Bq"
upstream_id
"chatcmpl-1e0e8f5c67a345e29db035e5c4ecae11"
provider_responses
0
endpoint_id
"b89a2f05-4051-4446-a9b0-7bc8ae7b7c90"
id
"chatcmpl-1e0e8f5c67a345e29db035e5c4ecae11"
is_byok
false
latency
1949
model_permaslug
"fireworks/ember-1-20260923"
provider_name
"Fireworks"
status
200
total_cost
0.038952
cache_discount
(null)
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
27.17%
Matches word count
n/a
neededClean
false
words
219
99.96%
Dialogue to Total Word Ratio
Ratio: 8.60%, Deviation: 1.40%
neededClean
false
wordsTotal
221
wordsDialogue
19
63.5636%