NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5XP8MFJS8PPNM57055FM5
Run Details
Model:
DeepSeek V3 (2025-03-24)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
17.5s
Cost:
$0.000255
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
Molly crouched behind a bush, binoculars trained on the festive chaos of a child’s birthday party. Balloons bobbed in the breeze, and a piñata hung menacingly from a tree. Bill adjusted his fake mustache—badly—and whispered, “You sure about this?” “Positive,” Molly said. “Presents are in the tent, guarded by a clown. Easy in, easy out.” “Clowns scare me.” “Professionally?” “Personally.” Molly rolled her eyes. “Here’s the plan: I’ll distract the clown with a tragic juggling accident. You grab the loot.” Bill frowned. “What if the kids cry?” “Then we’ll leave the consolation prizes.” “You mean the goody bags?” “Exactly. We’re thieves, not monsters.” Bill sighed. “Fine. But if that clown honks his nose at me, I’m out.” “Deal.” Molly stood, dusting off her pants. “Remember, Bill—speed, stealth, and no eating the cake.” “I make no promises.” They shared a grim nod and crept toward the party, unnoticed—until Bill tripped over a jump rope and face-planted into the bouncy castle. Molly groaned. “We’re gonna need a better distraction.” Bill’s muffled voice came from the inflatable depths: “Or a better partner!”
created_at
"2026-02-16T21:33:10.294409+00:00"
2/16/2026, 9:33:10 PM
model
"deepseek/deepseek-chat-v3-0324"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1693
moderation_latency
(null)
generation_time
17449
tokens_prompt
77
tokens_completion
354
native_tokens_prompt
66
native_tokens_completion
314
native_tokens_completion_images
(null)
native_tokens_reasoning
0
native_tokens_cached
23
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
0.00025498
router
(null)
provider_responses
0
id
"chatcmpl-a3befb8ee98e46be9d32134796bfb170"
status
200
is_byok
false
latency
102
endpoint_id
"a3938710-1b99-4a1f-85f4-2494f3f659d3"
provider_name
"ModelRun"
model_permaslug
"deepseek/deepseek-chat-v3-0324"
api_type
"completions"
id
"gen-1771277572-uGnid4ImngWEL0DW7vyN"
upstream_id
"chatcmpl-a3befb8ee98e46be9d32134796bfb170"
total_cost
0.00025498
cache_discount
(null)
upstream_inference_cost
0
provider_name
"ModelRun"
Evaluation details
Result
Evaluator
Details
Meta Data
51.9255%
Matches word count
n/a
neededClean
false
words
184
99.7769%
Dialogue to Total Word Ratio
Ratio: 52.17%, Deviation: 2.17%
neededClean
false
wordsTotal
184
wordsDialogue
96
75.8512%