NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-13-01M4TBJ0XHZ4SM9S311Y1APS08
Run Details
Model:
Ember-1 (Reasoning, Max)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
22.9s
Cost:
$0.019757
Provider:
Fireworks
Evaluation summary
Score
Evaluator
Details Link
99.74%
Matches word count
(details)
96.77%
Dialogue to Total Word Ratio
(details)
98.2547%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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 blueprint across the hood of the van. "Okay, Bill. Henderson kid's birthday, Saturday, two o'clock. Bounce house in the yard, clown by the cake table." "A clown? Molly, you know I can't do clowns." "Focus. We go in dressed as caterers." "What do caterers wear?" "Aprons, Bill. Just aprons." "Over our clothes, right?" "Obviously over our clothes. The presents will be stacked by the patio. I grab the big ones, you grab the small ones." "Why do I always get the small ones?" "Because last time you dropped a kayak off a balcony." "It was a canoe, and it was poorly wrapped." "Fine, you take medium gifts. Non-negotiable. And do not eat the cake." "Why would I eat the cake?" "Because at the museum job you ate the entire exhibit of historical cheeses." "That was research. What if a kid sees us?" "Tell him we're present inspectors." "That's not a real job." "Neither is robbing a six-year-old, yet here we are. Masks on at one-fifty." "Can my mask be a giraffe?" "It has to be, Bill. It's a giraffe-themed party." Bill sighed. "Best heist ever." "And if the clown talks to you, don't engage." "He'll engage me, Molly. They always do."
created_at
"2026-10-13T10:05:02.782Z"
10/13/2026, 10:05:02 AM
model
"fireworks/ember-1-20260923"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
576
moderation_latency
(null)
generation_time
22835
tokens_prompt
75
tokens_completion
1279
native_tokens_prompt
149
native_tokens_completion
1314
native_tokens_completion_images
(null)
native_tokens_reasoning
999
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
0.0197574
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791885902-T2RrC9VhiQlD81cNxBL0"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791885902-VlXC2vEgI5LmvRH2ZHOB"
upstream_id
"chatcmpl-e38f5d762b5040f2b2c3206430827f59"
provider_responses
0
endpoint_id
"b89a2f05-4051-4446-a9b0-7bc8ae7b7c90"
id
"chatcmpl-e38f5d762b5040f2b2c3206430827f59"
is_byok
false
latency
576
model_permaslug
"fireworks/ember-1-20260923"
provider_name
"Fireworks"
status
200
total_cost
0.0197574
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
96.77%
Dialogue to Total Word Ratio
Ratio: 94.26%, Deviation: 4.26%
neededClean
false
wordsTotal
209
wordsDialogue
197
98.2547%