NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5SRD018JZ6Y049R0S9GX8
Run Details
Model:
DeepSeek V3 (2024-12-26)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
13.9s
Cost:
$0.000332
Provider:
DeepInfra
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 adjusted her fake mustache in the rearview mirror, squinting at the reflection. "Bill, do I look like a clown yet?" Bill, sprawled in the passenger seat with a lollipop sticking out of his mouth, gave her a sidelong glance. "More like a walrus with commitment issues. But hey, kids love commitment issues." Molly rolled her eyes. "Fine. But if this fails, it’s your fault. You picked the mustache." "I picked the *idea* of a mustache. You’re the one who glued on half a sheep." "Focus, Bill. The party starts in ten minutes. What’s the plan again?" Bill leaned forward, tapping the dashboard like a drum. "Simple. You go in as Clown Molly, distract the kids with balloon animals that suspiciously look like grenades. I sneak in through the back, grab the presents, and meet you at the inflatable bouncy castle for our grand escape." "What about the parents?" Bill grinned, pulling out a megaphone from under his seat. "I’ll announce free ice cream in the parking lot. Parents can’t resist free ice cream. It’s science." Molly groaned. "This is the worst plan we’ve ever had." "Correction," Bill said, popping the lollipop out of his mouth. "It’s the worst plan we’ve ever *executed*. Big difference." They sat in silence for a moment before Molly sighed. "Let’s just get this over with. I hate clowns." "Funny," Bill said, shrugging. "Clowns hate you too."
created_at
"2026-02-16T21:30:57.974459+00:00"
2/16/2026, 9:30:57 PM
model
"deepseek/deepseek-chat-v3"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1112
moderation_latency
(null)
generation_time
13853
tokens_prompt
77
tokens_completion
368
native_tokens_prompt
66
native_tokens_completion
349
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
0.00033173
router
(null)
provider_responses
0
id
"chatcmpl-RtsSrYzQpKTCYTj97EthLOvt"
status
200
is_byok
false
latency
52
endpoint_id
"5294d55f-9012-496b-8f22-8cc919432dcd"
provider_name
"DeepInfra"
model_permaslug
"deepseek/deepseek-chat-v3"
api_type
"completions"
id
"gen-1771277443-6m0FMSKwNojgdgzJiWvD"
upstream_id
"chatcmpl-RtsSrYzQpKTCYTj97EthLOvt"
total_cost
0.00033173
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
0.0028%
Matches word count
n/a
neededClean
false
words
232
0.1550%
Dialogue to Total Word Ratio
Ratio: 65.95%, Deviation: 15.95%
neededClean
false
wordsTotal
232
wordsDialogue
153
0.0789%