NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-27-01KSMEF973FCKJH27FE52AHG3A
Run Details
Model:
Cydonia 24B V4.1
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
6.7s
Cost:
$0.000186
Provider:
Parasail
Evaluation summary
Score
Evaluator
Details Link
60.28%
Matches word count
(details)
93.27%
Dialogue to Total Word Ratio
(details)
76.7727%
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
"And you're sure this is going to work?" Molly asked, watching Bill tuck a rolled-up chloroform rag into his jacket pocket. "Composition notebook full of candy," Bill said brightly. "Kids love that stuff. What kid wouldn't want to help usher in a magical rainbow fairy." "Chloroforming a bunch of five-year-olds seems like the part where the plan goes off the rails." "Trust the process, Molly. They don't call me 'The Whisper' for nothing." "Is that what they call you? I thought it was 'Bill Who Always Gets Caught'." "Heard that one before. Anyway, I'll go in, do the whole rainbow fairy routine, and by the time they wake up, we're ghosts with their video games and portable electronic devices." "And the gifts they brought?" Molly crossed her arms. "How are you going to explain that?" "Oh, I'm not," Bill said, flashing her a grin. "Present thievery is the verb I answer to right now. Besides, the parents are the real mark. We'll replace the loot with decoder rings and stickers. Who doesn't love a box of chaos?" "You're planning to drug children and deceive their parents. We're terrible people." "That's why they pay us to do this," Bill said, adjusting his wizard hat. "Are we good? The clock's ticking on this arts and crafts theft."
created_at
"2026-05-27T10:07:52.047Z"
5/27/2026, 10:07:52 AM
model
"thedrummer/cydonia-24b-v4.1"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
223
moderation_latency
(null)
generation_time
6643
tokens_prompt
77
tokens_completion
327
native_tokens_prompt
243
native_tokens_completion
298
native_tokens_completion_images
(null)
native_tokens_reasoning
0
native_tokens_cached
240
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
0.0001859
router
(null)
provider_responses
0
endpoint_id
"4d46db86-63fe-47eb-85f1-6a7567af190c"
id
"chatcmpl-8331245548614fe98ab3345900bdd7a9"
is_byok
false
latency
223
model_permaslug
"thedrummer/cydonia-24b-v4.1"
provider_name
"Parasail"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.15.0; linux; x64))"
http_referer
(null)
request_id
"req-1779876472-dOk3bR8N9CR43tLBR2m3"
session_id
(null)
api_type
"completions"
id
"gen-1779876472-3upoMrK6tJph8OBEGcGL"
upstream_id
"chatcmpl-8331245548614fe98ab3345900bdd7a9"
total_cost
0.0001859
cache_discount
0.000036
upstream_inference_cost
0
provider_name
"Parasail"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
60.28%
Matches word count
n/a
neededClean
false
words
215
93.27%
Dialogue to Total Word Ratio
Ratio: 84.86%, Deviation: 5.14%
neededClean
false
wordsTotal
218
wordsDialogue
185
76.7727%