NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM612SSNV60Y0MZ7Q5Z097R
Run Details
Model:
DeepSeek V3 (2024-12-26)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
12.0s
Cost:
$0.000305
Provider:
DeepInfra
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 dim glow of a single bulb hung above the cluttered table, casting long shadows over Molly and Bill as they hunched over a hand-drawn map of the Johnson family’s backyard. Molly’s pencil tapped rhythmically against the edge of the paper, her brow furrowed in concentration. Bill leaned back in his chair, chewing on a toothpick, his eyes darting between the map and the clock on the wall. "Surveillance shows they’ll be distracted by the clown," Molly muttered, circling a patch of the map labeled "bounce house." Bill smirked. "Clowns. Always good for a diversion." Molly shot him a glare, her lips tightening. "Focus. We need a clean in-and-out. No hiccups." Bill shrugged, twirling the toothpick between his fingers. "Kid’s parties are easy pickings. Just grab the loot and go." Molly sighed, leaning forward to adjust the map. "It’s not just about the loot. It’s about precision. Timing. One wrong move, and we’re surrounded by screaming toddlers and angry parents." "Relax," Bill said, leaning closer. "We’ve got this. In and out, like you said." Molly hesitated, her eyes narrowing, but she nodded. The clock ticked louder as they finalized their plan, the tension in the room thickening like fog. Outside, the faint sound of laughter echoed in the distance—a reminder of the prize waiting just beyond their reach.
created_at
"2026-02-16T21:34:56.080242+00:00"
2/16/2026, 9:34:56 PM
model
"deepseek/deepseek-chat-v3"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
228
moderation_latency
(null)
generation_time
11973
tokens_prompt
77
tokens_completion
352
native_tokens_prompt
66
native_tokens_completion
319
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
0.00030503
router
(null)
provider_responses
0
id
"chatcmpl-RQjboF6d3EJ7vwtlo8n4AqCp"
status
200
is_byok
false
latency
50
endpoint_id
"5294d55f-9012-496b-8f22-8cc919432dcd"
provider_name
"DeepInfra"
model_permaslug
"deepseek/deepseek-chat-v3"
api_type
"completions"
id
"gen-1771277683-dDw9vqDX1Pg9fcvD22Wu"
upstream_id
"chatcmpl-RQjboF6d3EJ7vwtlo8n4AqCp"
total_cost
0.00030503
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
9.6081%
Matches word count
n/a
neededClean
false
words
222
0.0000%
Dialogue to Total Word Ratio
Ratio: 31.08%, Deviation: 21.08%
neededClean
false
wordsTotal
222
wordsDialogue
69
4.8041%