NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5D90KBGSYMNC7TGF022SK
Run Details
Model:
DeepSeek V3.1
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
12.7s
Cost:
$0.000509
Provider:
SambaNova
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
“You want us to hit a six-year-old’s birthday party?” Bill asked, lowering his newspaper. “The kid’s name is Bartholomew,” Molly stated, pointing at the elaborate map. “His father is a bubble bath tycoon. The haul will be epic.” “We’re gonna steal from a baby?” “We’re liberating overpriced plastic from a privileged infant, Bill. It’s practically a public service. Now, the main obstacle is the clown.” “Clowns are creepy. I’m not okay with clowns.” “The clown is a distraction. He’ll be busy making balloon poodles. That’s our window. You create a diversion.” “What kind of diversion?” “Spill the fruit punch. Claim a bee stung you. Start crying. I don’t know, improvise! I’ll grab the presents from the gift table.” “This feels wrong. What about the cake?” “The cake is not part of the job, Bill.” “It’s a three-tier chocolate fudge. It’s a shame to leave it.” “Fine! Grab a slice on the way out. But the big score is the new, unopened X-Station 5. That’s the payload. Are you in or not?” “I want the corner piece with the fondant race car.” “Deal. Now, let’s go over the exit strategy. The piñata’s a squealer.”
created_at
"2026-02-16T21:24:07.98606+00:00"
2/16/2026, 9:24:07 PM
model
"deepseek/deepseek-chat-v3.1"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
9707
moderation_latency
(null)
generation_time
12665
tokens_prompt
95
tokens_completion
336
native_tokens_prompt
67
native_tokens_completion
310
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
0.00050855
router
(null)
provider_responses
0
id
"0bf7ed21-b1bf-4c4d-9604-1f2152e5802e"
status
200
is_byok
false
latency
9706
endpoint_id
"9abe71b4-ff68-4f47-bf15-6cf4d76d9a80"
provider_name
"SambaNova"
model_permaslug
"deepseek/deepseek-chat-v3.1"
api_type
"completions"
id
"gen-1771277034-178T9O333dpBXmMyjai9"
upstream_id
"0bf7ed21-b1bf-4c4d-9604-1f2152e5802e"
total_cost
0.00050855
cache_discount
(null)
upstream_inference_cost
0
provider_name
"SambaNova"
Evaluation details
Result
Evaluator
Details
Meta Data
99.7443%
Matches word count
n/a
neededClean
false
words
196
97.7647%
Dialogue to Total Word Ratio
Ratio: 93.88%, Deviation: 3.88%
neededClean
false
wordsTotal
196
wordsDialogue
184
98.7545%