NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-13-01M4TAYER621BAZKD40RXY4EDN
Run Details
Model:
Ember-1 (Reasoning, Max)
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
33.7s
Cost:
$0.025337
Provider:
Fireworks
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
0.05%
Dialogue to Total Word Ratio
(details)
0.0251%
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 minivan. "Target: 42 Maple Drive. Saturday, two p.m. sharp." "That's a backyard," said Bill. "That's a fortress. Bounce house here, here, and—worst case scenario—here." She tapped three red X's. "Inflatable. Unpredictable. One gust of wind and you're eating vinyl." "What's the take?" "Forty presents, give or take. A bike, possible trampoline, a drone if Grandma came through." Molly clicked her pen. "Plus the pile by the patio table. That's the mother lode." Bill squinted at the diagram. "You've drawn a stick figure crying." "That's the mark. Timmy. Turns seven at approximately two-fifteen, when he realizes the gifts are gone." "Molly. We're robbing a child." "We're robbing thirty children, technically. Timmy just consolidates the inventory." She flipped to page two. "Now. Entry. We go in as the entertainment." "I'm not wearing the clown suit again." "You're wearing the clown suit again." "Last time a dog bit me." "That dog was part of the cover story and you know it." Bill crossed his arms. "What's my role?" "You juggle. Badly. Nobody watches a bad juggler. It's the perfect camouflage—people physically look away." Molly mimed a sad cascade of dropping balls. "Meanwhile, I work the gift table. Four minutes, maybe five. I've been practicing on your nephew's birthday." "You robbed my nephew?" "He's two. He wanted the box." "Okay," Bill said slowly. "Say we get the presents. How do we get out? Forty gifts don't fit in a clown car." "They fit in a clown van, which is what we have, which is why I borrowed your sister's minivan." "You told her we were going antiquing." "We are. These presents are about to become antiques. To Timmy." Bill rubbed his face. "What's the contingency?" "Piñata." "The piñata is the contingency?" "The piñata is always the contingency. Somebody cracks it open, every kid in the yard stampedes one direction. That's our window. Chaos. Screaming. Candy." Molly's eyes went soft. "Beautiful." "And if a kid catches us?" "You juggle at them." "And if a parent catches us?" "You juggle faster." Bill stared at the blueprint for a long moment. "Why are we doing this, Molly? There are banks. There are jewelry stores. There's a whole mall." Molly rolled up the blueprint and tucked it under her arm. "Because last year, Bill, I asked for one thing for my birthday. One thing. A Millennium Falcon Lego set. And you know what I got?" "Socks." "Socks." She climbed into the minivan. "This isn't about the presents. It was never about the presents." "It's a little bit about the presents." "Get in the van, Bill. We have a bounce house to case."
created_at
"2026-10-13T09:54:21.586Z"
10/13/2026, 9:54:21 AM
model
"fireworks/ember-1-20260923"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1070
moderation_latency
(null)
generation_time
33652
tokens_prompt
75
tokens_completion
1811
native_tokens_prompt
149
native_tokens_completion
1686
native_tokens_completion_images
(null)
native_tokens_reasoning
1026
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
0.0253374
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791885261-1e9FxH035nMbZTRrJDsZ"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791885261-0ybARfK1YHVQEgDOBFgz"
upstream_id
"chatcmpl-5e905c1f84444ba1845bce08a608907e"
provider_responses
0
endpoint_id
"b89a2f05-4051-4446-a9b0-7bc8ae7b7c90"
id
"chatcmpl-5e905c1f84444ba1845bce08a608907e"
is_byok
false
latency
1070
model_permaslug
"fireworks/ember-1-20260923"
provider_name
"Fireworks"
status
200
total_cost
0.0253374
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
0.00%
Matches word count
n/a
neededClean
false
words
446
0.05%
Dialogue to Total Word Ratio
Ratio: 82.33%, Deviation: 12.33%
neededClean
false
wordsTotal
447
wordsDialogue
368
0.0251%