NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5YQQGC9D651CSVKKBWGAG
Run Details
Model:
DeepSeek V3.1
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
8.9s
Cost:
$0.000304
Provider:
Novita
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
“So just to be clear,” Molly said, peering over her laptop. “The target is a six-year-old’s birthday party.” “The birthday boy is one Timothy Henderson,” Bill confirmed, pointing a finger at a crudely drawn map on the back of a napkin. “Intel suggests a soft target. Minimal security. One overweight Labrador retriever named ‘Snuffles’ who can be neutralized with a steak.” Molly sighed, pinching the bridge of her nose. “Bill, we stole the Crown Jewels.” “Exactly! And this is a cakewalk! In at 3:15, during the piñata chaos. Out by 3:25, before the cake-cutting ceremony causes a distraction we can’t exploit.” “And the exit strategy?” “The treehouse. It’s a perfect blind spot. We lower the loot down the slide, into the waiting wagon.” “The wagon?” “It’s a red Radio Flyer. Classic model. Very reliable.” Molly stared at him. “You’re telling me our getaway vehicle is a child’s wagon?” “It’s got those big, all-terrain wheels, Molly! Look, are you in or not? The clown arrives in an hour.” “Fine. But if I have to wear a party hat, I’m keeping my share of the LEGOs.”
created_at
"2026-02-16T21:33:36.331846+00:00"
2/16/2026, 9:33:36 PM
model
"deepseek/deepseek-chat-v3.1"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
777
moderation_latency
(null)
generation_time
8780
tokens_prompt
95
tokens_completion
313
native_tokens_prompt
68
native_tokens_completion
286
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
0.00030436
router
(null)
provider_responses
0
id
"2bb2387a-8c36-42b2-bdf9-00fed62cf217"
status
200
is_byok
false
latency
777
endpoint_id
"715d05e1-9fa7-4ceb-834a-833f5e26a55a"
provider_name
"Novita"
model_permaslug
"deepseek/deepseek-chat-v3.1"
api_type
"completions"
id
"gen-1771277606-aZO56w2Mx8X3nRyNuNmw"
upstream_id
"2bb2387a-8c36-42b2-bdf9-00fed62cf217"
total_cost
0.00030436
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Novita"
Evaluation details
Result
Evaluator
Details
Meta Data
81.2727%
Matches word count
n/a
neededClean
false
words
188
65.2261%
Dialogue to Total Word Ratio
Ratio: 81.91%, Deviation: 8.09%
neededClean
false
wordsTotal
188
wordsDialogue
154
73.2494%