NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM630YEJEF2E1BZM5H1KZJV
Run Details
Model:
DeepSeek V3 (2025-03-24)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
2.5s
Cost:
$0.000700
Provider:
Nebius
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
The dim glow of a flickering streetlight cast long shadows across the alley where Molly and Bill huddled over a crumpled napkin map. “This is the dumbest plan you’ve ever had,” Molly muttered, squinting at the scribbled layout of the backyard. “Breaking into a kid’s birthday party?” Bill grinned, adjusting his fake mustache. “Think about it—no security, no alarms, just cake-fueled chaos. We grab the loot and vanish before little Timmy blows out the candles.” Molly rolled her eyes. “And what’s our exit strategy? A getaway tricycle?” “Better.” Bill pulled out a pair of oversized clown shoes. “We blend in. Who’s gonna suspect clowns?” “Everyone. Clowns are terrifying.” “Exactly! Fear’s our ally. Plus, I packed confetti grenades.” He shook a glitter-filled balloon for emphasis. Molly sighed. “Fine. But if we get caught, I’m telling the cops you’re the mastermind.” “Deal.” Bill stuffed the map into his pocket. “Now, let’s move. The piñata’s got a five o’clock smash time, and I want first swing.” Molly groaned as they crept toward the sound of squealing children. “We’re gonna die in balloon animals.”
created_at
"2026-02-16T21:35:50.18788+00:00"
2/16/2026, 9:35:50 PM
model
"deepseek/deepseek-chat-v3-0324"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
718
moderation_latency
(null)
generation_time
2508
tokens_prompt
77
tokens_completion
326
native_tokens_prompt
66
native_tokens_completion
289
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
0.00069975
router
(null)
provider_responses
0
id
"chatcmpl-b6f2f139ba1e47ed8c498fc477b83325"
status
200
is_byok
false
latency
718
endpoint_id
"0dd6bc5a-8695-4d4d-8067-2f4ccf7e49e0"
provider_name
"Nebius"
model_permaslug
"deepseek/deepseek-chat-v3-0324"
api_type
"completions"
id
"gen-1771277747-XJ90L94W6EFUMHqVoOLp"
upstream_id
"chatcmpl-b6f2f139ba1e47ed8c498fc477b83325"
total_cost
0.00069975
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Nebius"
Evaluation details
Result
Evaluator
Details
Meta Data
43.3783%
Matches word count
n/a
neededClean
false
words
183
85.5601%
Dialogue to Total Word Ratio
Ratio: 56.28%, Deviation: 6.28%
neededClean
false
wordsTotal
183
wordsDialogue
103
64.4692%