NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5RYYYQ0AR4RCF8G7PM1QY
Run Details
Model:
DeepSeek V3 (2025-03-24)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
36.7s
Cost:
$0.000521
Provider:
Nebius
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’re kidding,” Molly said, adjusting her fake clown nose. “A kids’ party? That’s the big score?” Bill shrugged. “Easy in, easy out. No security, just cake-induced chaos. Plus, presents everywhere. Untapped market.” “Untapped—Bill, they’re wrapped in Toy Story paper.” “Exactly! Nobody suspects the clowns. We waltz in, distract ’em with balloon animals—” “You can’t make balloon animals.” “I’ll learn.” He waved a hand. “Point is, we grab the loot while they’re sugar-crashing. Clean, simple.” Molly pinched the bridge of her nose. “And when little Timmy catches us stuffing his new bike into a giant fake flower?” “Clown privilege. We’re above suspicion.” “Clown privilege isn’t a thing.” “It is today.” He tossed her a rainbow wig. “Look, worst case, we trip on our own shoes running away. Classic physical comedy. They’ll laugh so hard, they won’t call the cops.” Molly groaned. “If we get arrested, I’m telling them this was all your idea.” “Deal. But we’ll split the loot?” She sighed and slapped on the wig. “Fine. But if I have to honk a nose, I want the LEGOs.” “You drive a hard bargain.” Bill grinned. “Welcome to the world’s dumbest heist.”
created_at
"2026-02-16T21:30:54.766787+00:00"
2/16/2026, 9:30:54 PM
model
"deepseek/deepseek-chat-v3-0324"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1455
moderation_latency
(null)
generation_time
36545
tokens_prompt
77
tokens_completion
358
native_tokens_prompt
69
native_tokens_completion
324
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
0.0005205
router
(null)
provider_responses
0
id
"chatcmpl-a2c0e3d61353fa26"
status
200
is_byok
false
latency
1455
endpoint_id
"09c158fc-63e9-4c3a-813e-c952828ac296"
provider_name
"Nebius"
model_permaslug
"deepseek/deepseek-chat-v3-0324"
api_type
"completions"
id
"gen-1771277417-CFaPsEwseIjVhTdweUQY"
upstream_id
"chatcmpl-a2c0e3d61353fa26"
total_cost
0.0005205
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Nebius"
Evaluation details
Result
Evaluator
Details
Meta Data
97.6276%
Matches word count
n/a
neededClean
false
words
193
49.2925%
Dialogue to Total Word Ratio
Ratio: 80.83%, Deviation: 9.17%
neededClean
false
wordsTotal
193
wordsDialogue
156
73.4601%