NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-27-01KSMF8PD5JG15XP9H0C80F2BT
Run Details
Model:
Cydonia 24B V4.1
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
6.4s
Cost:
$0.000185
Provider:
Parasail
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
97.69%
Dialogue to Total Word Ratio
(details)
98.8060%
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
"Bill, we need a better distraction than you hopping around shouting 'kaboom' again." "In my defense, it worked at the pet show last year." "One elderly cat hissed at you. That doesn't count." "Details, Molly. It's all in the details." Molly sighed, tapping a blueprint of the party venue. "Look, the focus has to be on the parents. Where they look, we'll move. You need to start near the gift table and work your way inward, like a过了shark." "Orca, actually. Shark-like whales." "They're not sharks, Bill. Just follow the plan." "Relax, Molly. I've got this. The kids love me." "Bread crumbs love you. It's a different demographic." "All I'm saying is, the last time I was at a children's party—" "Bribed your way in." "—I won 'Best Adult Disguised as a Clown.' People remember that." "They remember calling security. We don't have time for your ego trip. If you mess this up, we lose the gear." "Wouldn't be the first time you ditched me after a 'botched' job." "I carry a change of clothes this time. All three outfits are cheaper than replacing your teeth after a parent gets the wrong idea." "Too soon. Too soon."
created_at
"2026-05-27T10:21:44.753Z"
5/27/2026, 10:21:44 AM
model
"thedrummer/cydonia-24b-v4.1"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
164
moderation_latency
(null)
generation_time
6324
tokens_prompt
77
tokens_completion
309
native_tokens_prompt
243
native_tokens_completion
296
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
0.0001849
router
(null)
provider_responses
0
endpoint_id
"4d46db86-63fe-47eb-85f1-6a7567af190c"
id
"chatcmpl-db6721447c374814a75485a3ec2d31d1"
is_byok
false
latency
164
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-1779877304-FZqbazef9MAj1UfL3Nnr"
session_id
(null)
api_type
"completions"
id
"gen-1779877304-LJId2Ru0rBPKOqC0Jlxw"
upstream_id
"chatcmpl-db6721447c374814a75485a3ec2d31d1"
total_cost
0.0001849
cache_discount
0.000036
upstream_inference_cost
0
provider_name
"Parasail"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.92%
Matches word count
n/a
neededClean
false
words
197
97.69%
Dialogue to Total Word Ratio
Ratio: 93.91%, Deviation: 3.91%
neededClean
false
wordsTotal
197
wordsDialogue
185
98.8060%