NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM634PK7T3Q0NHDREG4V6YD
Run Details
Model:
DeepSeek V3 (2024-12-26)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
12.2s
Cost:
$0.000325
Provider:
DeepInfra
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 dim glow of a single bulb flickered above Molly and Bill’s heads as they hunched over a crumpled napkin covered in scribbled plans. The faint scent of stale coffee lingered in the air. “Listen,” Molly whispered, jabbing a finger at the napkin. “The kid’s party is at 3 PM sharp. That’s when we strike.” Bill raised an eyebrow. “A child’s birthday party? Seriously? What are we stealing, crayons?” Molly rolled her eyes. “No, you idiot. The *presents*. Parents these days shell out serious cash for little Timmy’s robot dog or whatever.” Bill scratched his scruffy chin, considering this. “Fair point. But how do we get in without looking suspicious?” “We dress as clowns,” Molly said with a grin, pulling two oversized red noses from her bag. Bill stared at them, horrified. “Clowns? I hate clowns.” “Too bad,” Molly snapped. “It’s perfect. Everyone loves clowns—they’re practically invisible at parties. We blend in, grab the loot, and vanish before anyone notices.” Bill sighed, reluctantly taking a nose. “Fine. But if some kid asks me to make a balloon animal, I’m out.” Molly smirked. “Deal. Just remember—no stealing the cake.” “Noted,” Bill muttered, slipping the nose on. “This better be worth it.” “Trust me,” Molly said, adjusting her clown wig. “It’s going to be a *hilarious* heist.”
created_at
"2026-02-16T21:36:03.799405+00:00"
2/16/2026, 9:36:03 PM
model
"deepseek/deepseek-chat-v3"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
282
moderation_latency
(null)
generation_time
12204
tokens_prompt
77
tokens_completion
370
native_tokens_prompt
66
native_tokens_completion
341
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
0.00032461
router
(null)
provider_responses
0
id
"chatcmpl-R7avcLZ8QvzHT54tLQbC7O5F"
status
200
is_byok
false
latency
81
endpoint_id
"5294d55f-9012-496b-8f22-8cc919432dcd"
provider_name
"DeepInfra"
model_permaslug
"deepseek/deepseek-chat-v3"
api_type
"completions"
id
"gen-1771277751-juRjZvBguFxsZKLGLFvW"
upstream_id
"chatcmpl-R7avcLZ8QvzHT54tLQbC7O5F"
total_cost
0.00032461
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
43.3783%
Matches word count
n/a
neededClean
false
words
217
92.4153%
Dialogue to Total Word Ratio
Ratio: 55.30%, Deviation: 5.30%
neededClean
false
wordsTotal
217
wordsDialogue
120
67.8968%