NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-13-01M4TC4JPHTTGK9WX4S44JC8W1
Run Details
Model:
Ember-1 (Reasoning, Max)
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
27.8s
Cost:
$0.030237
Provider:
Fireworks
Evaluation summary
Score
Evaluator
Details Link
2.01%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
1.0065%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 500 word scene that has 70% 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 car. It was a crayon drawing of a backyard. "Okay, Bill. Focus. Saturday, two p.m., the Hendersons' place. Target: the gift table." Bill squinted. "Is that a giraffe?" "It's the bouncy castle. Brayden's mom drew it for me." "You got intel from the target's mom?" "She's in my book club. Now listen." Molly tapped the crayon fence. "We go in as entertainers. You're the clown." "I get vertigo in big shoes." "You're six feet tall, Bill. The shoes are the least of our problems." "What if the kids want balloon animals?" "Then make balloon animals." "I only know how to make a snake." "Every kid gets a snake. Moving on." She traced a finger to the patio. "The presents are here. Forty-plus gifts, untouched, guarded only by a sheet cake and Aunt Linda." "Linda a problem?" "Linda's a gossip. Keep her talking about her hip surgery, she won't notice a thing. I'll handle the cake." "We're stealing cake too?" "The cake's a diversion, Bill. I cut it, kids swarm, you load the wagon." "We have a wagon?" "We're stealing the wagon. It's in the yard. Radio Flyer. Cherry red. Practically a getaway vehicle." Bill scratched his chin. "What's the take, anyway? What does a seven-year-old even get?" Molly flipped open her notebook. "Registry says a LEGO Star Destroyer, a drone, two Nerf arsenals, and a karaoke machine." "A drone? For a child? I didn't get a drone till I was thirty." "You bought your own drone, Bill." "And I treasure it. So what's my cut, the karaoke machine?" "You can't carry a tune." "I can carry a machine." Molly pinched the bridge of her nose. "Fine. Karaoke's yours. I take the Star Destroyer." "Thought you didn't like LEGO." "I like three hundred dollars on eBay." "Fair." Bill folded his arms. "One concern. The piñata. What if a kid breaks it early and the candy panic throws off the timeline?" "The piñata's scheduled for three-thirty. We're gone by three-fifteen." "Scheduled?" "I read the Evite, Bill. There's an itinerary. These people are animals about punctuality." Bill whistled. "A backyard with an itinerary." "Rich suburb, buddy. Now, contingency. If a kid catches you loading gifts?" "Say I'm the present fairy?" "You are a grown man in clown paint." "Late present fairy. Birthday goblin?" "Say the magician needs them for the big finale." "What magician?" "You. You're the magician. The finale is the gifts disappearing." Bill's eyes went wide. "Molly. That's beautiful. The crime is the show." "The crime is the show," she agreed, rolling up the crayon blueprint. He was quiet a moment. "Do I get a cape?" "You get a cape." "Worth it, then. When do we rehearse?" "We don't rehearse a wagon loading, Bill." "I rehearse everything. I rehearsed ordering pizza this morning." "That explains the forty-minute phone call." "Nailed the rehearsal, though." Molly slid into the driver's seat. "Saturday. Two p.m. Big shoes, bigger smile. And Bill?" "Yeah?" "If you eat any of the cake, you're walking home." He considered this seriously. "What kind of cake?" "Bill." "What kind, Molly. I need to weigh my options."
created_at
"2026-10-13T10:15:10.811Z"
10/13/2026, 10:15:10 AM
model
"fireworks/ember-1-20260923"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
468
moderation_latency
(null)
generation_time
27729
tokens_prompt
75
tokens_completion
2085
native_tokens_prompt
149
native_tokens_completion
1986
native_tokens_completion_images
(null)
native_tokens_reasoning
1195
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
0.030237
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791886510-Npnbx9AbKrkjznbRWRzU"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791886510-DllD0V1Z8TfiR47riq2t"
upstream_id
"chatcmpl-f58cf76110b7464c86ee729a692ebf5c"
provider_responses
0
endpoint_id
"b89a2f05-4051-4446-a9b0-7bc8ae7b7c90"
id
"chatcmpl-f58cf76110b7464c86ee729a692ebf5c"
is_byok
false
latency
468
model_permaslug
"fireworks/ember-1-20260923"
provider_name
"Fireworks"
status
200
total_cost
0.030237
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
2.01%
Matches word count
n/a
neededClean
false
words
525
0.00%
Dialogue to Total Word Ratio
Ratio: 84.93%, Deviation: 14.93%
neededClean
false
wordsTotal
531
wordsDialogue
451
1.0065%