NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5JYF70RK1SQZM5SK1HC6T
Run Details
Model:
DeepSeek V3.1
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
19.8s
Cost:
$0.000230
Provider:
SambaNova
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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
The warehouse was drafty, smelling of diesel and desperation. Molly tapped the blueprints with a manicured finger. “Alright. The birthday brat—Timmy—turns seven at two PM. That’s our window.” Bill stared, a sausage halfway to his mouth. “We’re hitting a kiddie party? For a pile of Legos and a probably-drooled-on teddy bear?” “It’s the Henderson job. That ‘teddy bear’ is a limited-edition Steiff bear worth five grand. The ‘Legos’ are a solid gold vintage castle set. Their security is complacent, sentimental. The dad’s a collector. This is a goldmine wrapped in wrapping paper.” Bill chewed thoughtfully. “What’s the play? I’m not going as a clown, Moll. I’ve got a reputation.” “You’re the distractingly bad magician. I’ll be the disgruntled caterer. You cause a scene with a poorly executed dove trick—” “Hey!” “—while I load the gift table into a rental stroller. We’re in and out during the piñata chaos. They’ll blame a sugar-crazed six-year-old.” Bill sighed, looking at his reflection in a polished wrench. “A magician. Fine. But if I have to say ‘abracadabra,’ I want a bigger cut.”
created_at
"2026-02-16T21:27:23.925595+00:00"
2/16/2026, 9:27:23 PM
model
"deepseek/deepseek-chat-v3.1"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1672
moderation_latency
(null)
generation_time
19771
tokens_prompt
95
tokens_completion
315
native_tokens_prompt
67
native_tokens_completion
293
native_tokens_completion_images
(null)
native_tokens_reasoning
0
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.0002298
router
(null)
provider_responses
0
id
"bbcc741c-57ef-4c3b-a7df-7b556bd55bec"
status
200
is_byok
false
latency
1671
endpoint_id
"1dda4bb9-c626-4816-bb54-99665323fef0"
provider_name
"SambaNova"
model_permaslug
"deepseek/deepseek-chat-v3.1"
api_type
"completions"
id
"gen-1771277220-CCnUHemw3iyOFjx5txJT"
upstream_id
"bbcc741c-57ef-4c3b-a7df-7b556bd55bec"
total_cost
0.0002298
cache_discount
(null)
upstream_inference_cost
0
provider_name
"SambaNova"
Evaluation details
Result
Evaluator
Details
Meta Data
68.1022%
Matches word count
n/a
neededClean
false
words
186
0.0000%
Dialogue to Total Word Ratio
Ratio: 79.57%, Deviation: 29.57%
neededClean
false
wordsTotal
186
wordsDialogue
148
34.0511%