NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5KGAYEMKGM6H22VTA7V2Z
Run Details
Model:
DeepSeek V3 (2025-03-24)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
9.5s
Cost:
$0.000267
Provider:
ModelRun
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 warehouse was dim, save for the flickering bulb above Molly and Bill’s heads. A hand-drawn map of the neighborhood sprawled across the table, dotted with crude Stars of David next to the words *MEGA PARTY*. “This is low, even for us,” Bill muttered, scratching his stubble. “Stealing from a kid’s birthday?” Molly rolled her eyes. “Please. Kids lose interest in toys after, what, five minutes? We’re doing them a favor.” She tapped the map. “Security’s a joke—just a clown with a balloon animal addiction.” Bill sighed. “And the parents?” “Distracted by cheap champagne and tiny sandwiches. We slip in disguised as magicians—*poof*, grab the loot, vanish.” “What if the clown’s suspicious?” “Clowns are legally obligated to be terrible judges of character,” Molly said, shoving a rubber chicken into her bag. “Trust me.” Bill hesitated. “I dunno. Kids got those creepy○○○ staticky things.” “Static cling? That’s laundry.” “You know what I mean!” Molly tossed him a fake mustache. “Bill, either we walk out with a haul of unopened Legos, or we don’t. That’s capitalism.” Bill groaned. “Fine. But if we get tackled by a sugar-crazed six-year-old, I’m blaming you.” “Deal.” Molly grinned. “Now let’s go commit some festive felony.”
created_at
"2026-02-16T21:27:28.792604+00:00"
2/16/2026, 9:27:28 PM
model
"deepseek/deepseek-chat-v3-0324"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1115
moderation_latency
(null)
generation_time
9487
tokens_prompt
77
tokens_completion
371
native_tokens_prompt
66
native_tokens_completion
329
native_tokens_completion_images
(null)
native_tokens_reasoning
0
native_tokens_cached
5
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
0.00026653
router
(null)
provider_responses
0
id
"chatcmpl-73546927098445c586532c15f7662f0f"
status
200
is_byok
false
latency
88
endpoint_id
"a3938710-1b99-4a1f-85f4-2494f3f659d3"
provider_name
"ModelRun"
model_permaslug
"deepseek/deepseek-chat-v3-0324"
api_type
"completions"
id
"gen-1771277238-kFv55jf13QFn1No0HCvP"
upstream_id
"chatcmpl-73546927098445c586532c15f7662f0f"
total_cost
0.00026653
cache_discount
(null)
upstream_inference_cost
0
provider_name
"ModelRun"
Evaluation details
Result
Evaluator
Details
Meta Data
99.7443%
Matches word count
n/a
neededClean
false
words
204
1.6842%
Dialogue to Total Word Ratio
Ratio: 64.22%, Deviation: 14.22%
neededClean
false
wordsTotal
204
wordsDialogue
131
50.7143%