NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM63064GSYBA8QNS5B52KF0
Run Details
Model:
DeepSeek V3 (2024-12-26)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
14.1s
Cost:
$0.000327
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 peered over the fence, her eyes gleaming. “Alright, Bill, here’s the plan. We sneak in during the piñata chaos, grab the loot, and hightail it out before anyone notices.” Bill scratched his head. “Piñata chaos? Molly, we’re stealing from a kid’s party, not staging a coup.” “Exactly! It’s the perfect distraction. Kids screaming, candy flying—no one’s gonna notice two adults hauling gifts into a van.” Bill frowned. “What if there’s security?” “Security? At a five-year-old’s birthday? Bill, the only threat here is a sugar rush and maybe a rogue clown.” “Clowns?” Bill paled. “You didn’t say anything about clowns.” “Relax, it’s probably just Uncle Jerry in a wig. Focus. We need disguises.” Bill sighed. “Fine. But I’m not wearing a tutu.” Molly smirked. “Too bad. It would’ve really sold the ‘helpful party planner’ vibe.” “Molly, this is insane.” “Insane? Bill, we’re stealing presents from children. Insane went out the window when we agreed to this. Now, grab the glitter glue and let’s blend in.” Bill groaned. “I can’t believe I let you talk me into this.” “Yeah, yeah. Save the drama for the getaway. And remember—no eye contact with the birthday kid. She’ll sniff us out like a bloodhound.” “Right. Because that’s the part of this plan I’m worried about.”
created_at
"2026-02-16T21:36:01.149646+00:00"
2/16/2026, 9:36:01 PM
model
"deepseek/deepseek-chat-v3"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
281
moderation_latency
(null)
generation_time
14018
tokens_prompt
77
tokens_completion
381
native_tokens_prompt
66
native_tokens_completion
344
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
0.00032728
router
(null)
provider_responses
0
id
"chatcmpl-RtEzmvMaC5dyJOsgZPgWuxCl"
status
200
is_byok
false
latency
49
endpoint_id
"5294d55f-9012-496b-8f22-8cc919432dcd"
provider_name
"DeepInfra"
model_permaslug
"deepseek/deepseek-chat-v3"
api_type
"completions"
id
"gen-1771277746-TQ6KZPf4XihcXbyeZF9w"
upstream_id
"chatcmpl-RtEzmvMaC5dyJOsgZPgWuxCl"
total_cost
0.00032728
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
60.2752%
Matches word count
n/a
neededClean
false
words
215
100.0000%
Dialogue to Total Word Ratio
Ratio: 89.77%, Deviation: 0.23%
neededClean
false
wordsTotal
215
wordsDialogue
193
80.1376%