NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2J44HPDAK8E78E24GBSX63
Run Details
Model:
DeepSeek V4 Flash (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
6.7s
Cost:
$0.000128
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
0.03%
Matches word count
(details)
0.01%
Dialogue to Total Word Ratio
(details)
0.0193%
Overall
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 flattened the crumpled party invitation against the dashboard. “So the loot is in a bounce castle? That’s your intel?” Bill adjusted his balaclava, a child’s party hat perched sideways on his head. “It’s a premium inflatable. Parents dump gifts inside for the ‘surprise reveal’.” He pointed. “We hit the zip-door, grab the haul, exit through the face-painting station.” Molly frowned. “And the twelve sugar-high seven-year-olds?” “Distraction.” Bill produced a bag of loud squeaky toys. “I launch these. Chaos ensues. You, with your nimble fingers, unzip and grab.” “My nimble fingers are currently cold,” Molly said, blowing on them. “And what about the clown? He looks suspicious.” “Clown’s on break. Eating a hot dog behind the catering van. I saw him.” Molly squinted at the rainbow-colored castle. “And you’re certain the presents aren’t just… empty boxes? For the magic trick?” Bill’s face fell. “Oh, for the love of— No, they’re real. The mother posted the haul on social media. Mountain of LEGO sets. A drone. Gift cards.” “Alright,” Molly sighed. “But if I get face-painted as a butterfly against my will, you’re doing the next job solo.” Bill grinned. “Deal. On my count: three, two—” A child’s shriek pierced the air. The clown, mustard on his chin, was advancing toward their car. “Abort!” Molly hissed. “We’re going to need a bigger distraction.” Bill grabbed the squeaky toys. “I’ve got this.”
created_at
"2026-04-25T14:53:57.69Z"
4/25/2026, 2:53:57 PM
model
"deepseek/deepseek-v4-flash-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
551
moderation_latency
(null)
generation_time
6562
tokens_prompt
77
tokens_completion
473
native_tokens_prompt
67
native_tokens_completion
424
native_tokens_completion_images
(null)
native_tokens_reasoning
60
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
num_fetches
(null)
web_search_engine
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.0001281
router
(null)
provider_responses
0
endpoint_id
"722e0746-2034-4d6e-a08f-e6271849ee9e"
id
"746c3d26-cf03-4c0c-803c-ddab3ec4907a"
is_byok
false
latency
281
model_permaslug
"deepseek/deepseek-v4-flash-20260423"
provider_name
"DeepSeek"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777128837-UcXcO6XW1H97O2CJbZCZ"
session_id
(null)
api_type
"completions"
id
"gen-1777128837-G6e2MF8WDbdHgKfQVRMn"
upstream_id
"746c3d26-cf03-4c0c-803c-ddab3ec4907a"
total_cost
0.0001281
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepSeek"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
0.03%
Matches word count
n/a
neededClean
false
words
230
0.01%
Dialogue to Total Word Ratio
Ratio: 67.51%, Deviation: 17.51%
neededClean
false
wordsTotal
237
wordsDialogue
160
0.0193%