NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM62KK72A70WMJWX9P5BRNP
Run Details
Model:
DeepSeek V3 (2024-12-26)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
11.3s
Cost:
$0.000259
Provider:
DeepInfra
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
"Molly, are you really suggesting we steal presents from a bunch of six-year-olds?" Bill whispered, crouched behind a hedge outside the brightly decorated house. "Not just any six-year-olds," Molly said, adjusting her black ski mask. "These are *rich* six-year-olds. Their gifts are probably gold-plated or something." "Gold-plated? They’re kids, Mol. They’re probably getting stuffed unicorns and coloring books." "Exactly! Minimal resale value, sure, but think of the *volume*. We fill the van, hit a few more parties, and boom—Christmas is payday." Bill frowned. "What if one of them wakes up? Kids are unpredictable. What do we do, wrestle a toddler?" "Easy," Molly said, pulling a candy bar from her pocket. "Distract ’em with sugar. Works every time." "And what if they scream?" "We scream louder. Pretend we’re clowns or something. Who’s gonna question clowns at a kid’s party?" Bill groaned. "This is the worst idea you’ve ever had." "Worst idea *so far*," Molly corrected, grinning. "Now, grab the sack and follow my lead. And don’t step on any Legos."
created_at
"2026-02-16T21:35:45.341451+00:00"
2/16/2026, 9:35:45 PM
model
"deepseek/deepseek-chat-v3"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
359
moderation_latency
(null)
generation_time
11316
tokens_prompt
77
tokens_completion
288
native_tokens_prompt
66
native_tokens_completion
267
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
0.00025875
router
(null)
provider_responses
0
id
"chatcmpl-RqlOIYpFsS98CIfetD0H7k5k"
status
200
is_byok
false
latency
50
endpoint_id
"5294d55f-9012-496b-8f22-8cc919432dcd"
provider_name
"DeepInfra"
model_permaslug
"deepseek/deepseek-chat-v3"
api_type
"completions"
id
"gen-1771277733-rLtLSue2EFGzcVPQZdIh"
upstream_id
"chatcmpl-RqlOIYpFsS98CIfetD0H7k5k"
total_cost
0.00025875
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
9.6081%
Matches word count
n/a
neededClean
false
words
178
50.3542%
Dialogue to Total Word Ratio
Ratio: 80.90%, Deviation: 9.10%
neededClean
false
wordsTotal
178
wordsDialogue
144
29.9812%