NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5BB46QM2QS5G9DKCY4HWV
Run Details
Model:
DeepSeek V3 (2025-03-24)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
11.0s
Cost:
$0.000278
Provider:
ModelRun
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
Molly peered through the binoculars at the bustling children’s party in the backyard. “You’re sure they don’t have a guard dog?” she muttered. Bill rolled his eyes, adjusting his fake mustache. “Relax, it’s a six-year-old’s birthday, not Fort Knox. Worst we got is a clown with balloon animals.” “Balloon animals are no joke,” Molly snapped. “One popped near me last year, and I still have nightmares.” Bill sighed. “Focus. We sneak in disguised as caterers, load the gifts into the cake van, and boom—retirement fund.” “What if the kids notice?” “Kids are easily distracted. Drop a piñata, and they’ll lose their minds.” Molly chewed her lip. “And the parents?” Bill grinned. “Spiked punch. Non-alcoholic, obviously. Just… sleepy.” “That’s evil.” “It’s efficient.” Bill tossed her a hairnet. “Now put this on. You’re ‘Susan from catering.’” Molly glared at the hairnet. “Susan wouldn’t be caught dead in this.” “Susan’s a professional,” Bill hissed. “And professionals don’t whine about heists involving goody bags.” Molly grumbled but slipped the hairnet on. “If we get caught, I’m blaming Susan.” Bill adjusted his nametag. “Fair. But if we pull this off, we’re buying a yacht.” “With what money?” He winked. “The kids’ college funds.”
created_at
"2026-02-16T21:23:02.975684+00:00"
2/16/2026, 9:23:02 PM
model
"deepseek/deepseek-chat-v3-0324"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2439
moderation_latency
(null)
generation_time
10606
tokens_prompt
77
tokens_completion
387
native_tokens_prompt
66
native_tokens_completion
344
native_tokens_completion_images
(null)
native_tokens_reasoning
0
native_tokens_cached
4
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
0.00027808
router
(null)
provider_responses
0
status
429
is_byok
false
latency
55
endpoint_id
"820376cb-f110-4d56-ab52-5bd6ca269420"
provider_name
"DeepInfra"
model_permaslug
"deepseek/deepseek-chat-v3-0324"
1
id
"chatcmpl-f12d63b84e8f4d979db152de17ef3b93"
status
200
is_byok
false
latency
124
endpoint_id
"a3938710-1b99-4a1f-85f4-2494f3f659d3"
provider_name
"ModelRun"
model_permaslug
"deepseek/deepseek-chat-v3-0324"
api_type
"completions"
id
"gen-1771276971-RZEafedkbgosCRZUtnG1"
upstream_id
"chatcmpl-f12d63b84e8f4d979db152de17ef3b93"
total_cost
0.00027808
cache_discount
(null)
upstream_inference_cost
0
provider_name
"ModelRun"
Evaluation details
Result
Evaluator
Details
Meta Data
99.9840%
Matches word count
n/a
neededClean
false
words
202
0.0000%
Dialogue to Total Word Ratio
Ratio: 71.29%, Deviation: 21.29%
neededClean
false
wordsTotal
202
wordsDialogue
144
49.9920%