NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-27-01KSMEX1FYAE3YDBPBQ4GXQBE4
Run Details
Model:
Skyfall 36B V2
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
6.2s
Cost:
$0.000314
Provider:
Parasail
Evaluation summary
Score
Evaluator
Details Link
43.38%
Matches word count
(details)
58.57%
Dialogue to Total Word Ratio
(details)
50.9754%
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 adjusted her striped shirt and tucked a curlicue of her blonde wig behind her ear. "Bill-bones, are you sure we're not going to hell for stealing from children?" Bill lowered his goggles and grinned. "Molls, we do this for the thrill, not the stuff. Think of this as our Robin Hood phase. We take from the rich, give to the... well, you know." "I'm not sure about this. Whose idea was it again, Steely to do an actual heist that wasn't fancy-food-snatching?" She frowned, suppressing a smirk. "I got a tip from some mother. Apparently, these parents are loaded, but won't invest a cent. If it helps the economy though, I say we take their fancy presents!" She sighs, shaking her head as she nods in appreciation. "Let me see if I got this straight. We sneak in when the kids are distracted by cupcakes — and Woo Woo, rocking his new crooner skills." "Close, he’ll be moonlighting as ‘Willy Wonka’ for the show." "I can’t imagine what unlicensed ice cream and candy-stuffed incognito parkas will get us." Bill’s eyes went wide. "Exactly! This heist could melt the ice cream in an abandoned warehouse — that’s how it becomes our Aladdin’s lamp. We’re breaking in to give the kids a night in which they're the grand prize bidders."
created_at
"2026-05-27T10:15:22.891Z"
5/27/2026, 10:15:22 AM
model
"thedrummer/skyfall-36b-v2"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
210
moderation_latency
(null)
generation_time
6011
tokens_prompt
77
tokens_completion
329
native_tokens_prompt
243
native_tokens_completion
315
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
0.00031365
router
(null)
provider_responses
0
endpoint_id
"1eb01ded-ae11-49e6-8aa6-3067584070bd"
id
"chatcmpl-b4401bc03ca61039"
is_byok
false
latency
210
model_permaslug
"thedrummer/skyfall-36b-v2"
provider_name
"Parasail"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.15.0; linux; x64))"
http_referer
(null)
request_id
"req-1779876922-tqQYFVSmN6tcyh6tUDPZ"
session_id
(null)
api_type
"completions"
id
"gen-1779876922-B31NKPu6L2Q01e5LtJRc"
upstream_id
"chatcmpl-b4401bc03ca61039"
total_cost
0.00031365
cache_discount
0.000072
upstream_inference_cost
0
provider_name
"Parasail"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
43.38%
Matches word count
n/a
neededClean
false
words
217
58.57%
Dialogue to Total Word Ratio
Ratio: 81.45%, Deviation: 8.55%
neededClean
false
wordsTotal
221
wordsDialogue
180
50.9754%