NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-13-01M4TAXWWDY68TF075Z6SE9JBV
Run Details
Model:
Ember-1 (Reasoning, Max)
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
38.3s
Cost:
$0.031097
Provider:
Fireworks
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
0.29%
Dialogue to Total Word Ratio
(details)
0.1460%
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, weighing the corners down with a juice box and a half-eaten string cheese. "Right," she said. "Target: 44 Maple Drive. Saturday, two p.m. The Henderson kid turns seven." Bill squinted at the diagram. "Is this floor plan drawn in crayon?" "His older sister drew it. I paid her in gum." Molly tapped the paper. "Front door's a no-go. Bouncy castle's got sightlines over the whole yard." "Bouncy castle," Bill repeated. "So we're talking countermeasures." "Countermeasures," Molly confirmed. "The clown's name is Giggles. Ex-military, probably. They always are. He'll be doing balloon animals near the gift table from two-fifteen onward. That's our window." "What if he makes a balloon giraffe?" "Then we go to plan B." "What's plan B?" "I haven't thought of it yet, but it involves a lot of running." Bill pulled a notepad from his jacket. "Walk me through the score. What are we actually looking at?" Molly produced a photograph, slightly blurry, clearly taken through a hedge. "Thirty-two presents, gift table, northeast corner. The big one's a bike. Red. Tasha's cousin works at the toy store, says the mom spent four hundred on it." "We're stealing a child's bicycle." "We're liberating a child's bicycle. Big difference. One of us sleeps at night." Bill considered this. "What about the piñata?" "Off limits. Piñata's got emotional value. We're thieves, Bill, not monsters." "And the cake?" Molly hesitated. "The cake is negotiable." "You said no cake." "I said the cake is negotiable, which is what you say when you want the cake but don't want to be judged." Bill made a note. "Getaway?" "Minivan. We blend in. Every car on that street is a minivan. We'll be invisible." She rolled up the blueprint. "One more thing. The kids." "What about them?" "Twenty of them. Sugar-fueled. Fast. If the grab goes loud, they swarm. You ever been taken down by a seven-year-old?" "No." "Pray you never are. They go for the knees. It's pack behavior." Bill shuddered. "Dogs?" "One. A golden retriever named Biscuit. He's on the payroll." "You bribed a dog." "I bribed a dog. Two hot dogs a day for a week, and on Saturday, Biscuit looks the other way." Molly checked her watch. "Synchronize. We go in at two-fifteen, grab window's eleven minutes, out by two-twenty-six. Nobody gets hurt, nobody cries, nobody pops a balloon near my ear. You know how I feel about balloons." "Noted." "And Bill?" "Yeah?" "If you eat cake at the scene, I'm leaving you behind." Bill slowly put the fork back in his pocket. "How did you—" "I know you."
created_at
"2026-10-13T09:54:03.289Z"
10/13/2026, 9:54:03 AM
model
"fireworks/ember-1-20260923"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
486
moderation_latency
(null)
generation_time
38297
tokens_prompt
75
tokens_completion
2042
native_tokens_prompt
149
native_tokens_completion
2070
native_tokens_completion_images
(null)
native_tokens_reasoning
1397
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
0.0310974
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791885243-f9y3g6ajAqGRcjBJCa5b"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791885243-1RBMkbxDNWAFJVrID8k4"
upstream_id
"chatcmpl-dc4674de044d4927b7e0d5a845cf6c40"
provider_responses
0
endpoint_id
"b89a2f05-4051-4446-a9b0-7bc8ae7b7c90"
id
"chatcmpl-dc4674de044d4927b7e0d5a845cf6c40"
is_byok
false
latency
486
model_permaslug
"fireworks/ember-1-20260923"
provider_name
"Fireworks"
status
200
total_cost
0.0310974
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
437
0.29%
Dialogue to Total Word Ratio
Ratio: 80.80%, Deviation: 10.80%
neededClean
false
wordsTotal
448
wordsDialogue
362
0.1460%