NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5NJ29XH6HHZA32N2PYPFF
Run Details
Model:
DeepSeek V3 (2025-03-24)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
7.6s
Cost:
$0.000342
Provider:
SiliconFlow
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 adjusted her plastic clown nose and sighed. “This is the dumbest plan we’ve ever had, Bill.” Bill tightened his rainbow wig. “Nah, nah, think about it. No security, no alarms—just cake, kids, and full-on chaos. Easiest score of our lives.” “We’re dressed as clowns, Bill. Clowns. You know what kids do to clowns? They scream. They cry. They throw cake.” “Exactly!” Bill grinned. “While they’re busy losing their tiny minds, we grab the presents and hightail it out the back. No one suspects the clowns.” Molly folded her arms. “And how do we explain a sack full of toys to the getaway driver?” “Uh… charity?” “Oh, sure. Two known thieves suddenly get philanthropic?” Bill wiggled his oversized shoes. “Look, if it goes south, we’ll just say we’re performance artists.” “Performance artists don’t steal LEGO sets, Bill.” “They do if the art is commentary on consumerism!” Molly groaned. “Fine. But if one of those little demons bites me, I’m throwing you under the bouncy castle.” “Deal. Now let’s go make some memories—mostly traumatic ones.” Molly sighed. “I hate this job.” Bill adjusted his red nose. “No, you don’t. You love it.” She smirked. “Yeah. I really do.”
created_at
"2026-02-16T21:28:34.030537+00:00"
2/16/2026, 9:28:34 PM
model
"deepseek/deepseek-chat-v3-0324"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1718
moderation_latency
(null)
generation_time
7490
tokens_prompt
77
tokens_completion
358
native_tokens_prompt
66
native_tokens_completion
325
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
0.0003415
router
(null)
provider_responses
0
id
"019c685ac9f5ee9d206fe7f179ae8b56"
status
200
is_byok
false
latency
1713
endpoint_id
"d562908f-c5eb-4a32-9a91-24d53b176fd8"
provider_name
"SiliconFlow"
model_permaslug
"deepseek/deepseek-chat-v3-0324"
api_type
"completions"
id
"gen-1771277305-plggKY4wYdlj3uq2wTfu"
upstream_id
"019c685ac9f5ee9d206fe7f179ae8b56"
total_cost
0.0003415
cache_discount
(null)
upstream_inference_cost
0
provider_name
"SiliconFlow"
Evaluation details
Result
Evaluator
Details
Meta Data
100.0000%
Matches word count
n/a
neededClean
false
words
200
72.8763%
Dialogue to Total Word Ratio
Ratio: 82.50%, Deviation: 7.50%
neededClean
false
wordsTotal
200
wordsDialogue
165
86.4382%