NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5NJVMGES25GM8YG0031RJ
Run Details
Model:
DeepSeek V3.1
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
31.3s
Cost:
$0.000248
Provider:
DeepInfra
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 peered through the binoculars, her face a mask of grim determination. “The target is heavily fortified,” she whispered. “Multiple small, hyper-vigilant guards. Code names: ‘Timmy’ and ‘Chloe’.” Bill, crouched beside her, consulted a hand-drawn map on a napkin. “The presents are stored in the primary location—the living room. Our window is during the cake distraction. Chaos theory suggests a ninety-second blind spot.” He pointed a pudgy finger at the schematic. “You create a diversion with the piñata. I’ll move in, secure the goods in the empty gift bag, and exfiltrate via the sandbox. It’s clean.” Molly lowered the binoculars, a skeptical eyebrow arched. “Your last ‘clean’ plan involved a trebuchet and a startled swan. Are the intel reports on the parental units confirmed?” “The dad is already snoring on the patio furniture. The mom is on her third glass of ‘juice’. The coast will be clear.” He adjusted his black beanie. “This is the big one, Moll. A haul of LEGOs, action figures, those squishy things… we retire.” Molly sighed, checking the time. “Fine. But if one of those tiny guards offers me a juice box, I’m taking it. A pro needs hydration.” They moved out, blending into the suburban shrubbery.
created_at
"2026-02-16T21:28:58.846695+00:00"
2/16/2026, 9:28:58 PM
model
"deepseek/deepseek-chat-v3.1"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
938
moderation_latency
(null)
generation_time
31187
tokens_prompt
95
tokens_completion
337
native_tokens_prompt
67
native_tokens_completion
303
native_tokens_completion_images
(null)
native_tokens_reasoning
0
native_tokens_cached
64
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
0.0002483200000128
router
(null)
provider_responses
0
id
"cmpl-9316f10a325f426ea591fda2f454c6d1"
status
200
is_byok
false
latency
150
endpoint_id
"012f7d1f-23d4-4d03-9aa3-432d8ad82757"
provider_name
"DeepInfra"
model_permaslug
"deepseek/deepseek-chat-v3.1"
api_type
"completions"
id
"gen-1771277306-JTXQyxqHoNOhjCgxxxLC"
upstream_id
"cmpl-9316f10a325f426ea591fda2f454c6d1"
total_cost
0.0002483200000128
cache_discount
0.0000051199999872
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
98.7124%
Matches word count
n/a
neededClean
false
words
206
0.0000%
Dialogue to Total Word Ratio
Ratio: 70.87%, Deviation: 60.87%
neededClean
false
wordsTotal
206
wordsDialogue
146
49.3562%