NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2EFH2BA5C287M36P9PF07W
Run Details
Model:
DeepSeek V4 Flash (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
3m 30s
Cost:
$0.000116
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
60.28%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
30.1376%
Overall
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 bouncy castle sagged under the weight of a sobering truth: they were, by all accounts, adults. Molly adjusted her fake pigtails, which itched like a nest of angry ants. Bill was wedged into a child-sized unicorn costume, his knees knocking against his chin. “The target is in the gift tent, behind the piñata,” Molly whispered, voice a strained rasp. “Roger that, Rainbow Sparkle,” Bill squeaked, his horn flopping. “But my hooves are cramping.” A shriek of delight erupted from a nearby jungle gym. Molly glared. “The window is three minutes. I create a diversion with the bubble machine. You enter, grab the loot bag, exit through the cake table.” “Cake. Right.” Bill’s eyes glazed over. “Focus!” She jabbed a finger at his mane. “Presents first. Then maybe we lick the frosting off the floor.” A toddler wandered past, staring at Bill’s ungainly bulk. “Why is that unicorn crying?” “Allergic to joy,” Molly snapped, then lowered her voice. “On my signal. If the mom with the juice box sees you, just do the shuffle. You know, the one where you look like you need a diaper change.” Bill groaned, his horn scraping a low-hanging balloon. “I hate this plan.” “You love it. You’re just scared of the glitter.” She grinned. “Now go steal some dreams.”
created_at
"2026-04-25T13:50:16.656Z"
4/25/2026, 1:50:16 PM
model
"deepseek/deepseek-v4-flash-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
5999
moderation_latency
(null)
generation_time
209757
tokens_prompt
77
tokens_completion
421
native_tokens_prompt
67
native_tokens_completion
381
native_tokens_completion_images
(null)
native_tokens_reasoning
69
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
0.00011606
router
(null)
provider_responses
0
endpoint_id
"934a69f9-bd54-474b-beca-24560f721e12"
id
"f9ececc716174ffd80d160a8ffec6bbe"
is_byok
false
latency
48
model_permaslug
"deepseek/deepseek-v4-flash-20260423"
provider_name
"DeepInfra"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777125016-ZZwZedmUyCP5kEEAwKY0"
session_id
(null)
api_type
"completions"
id
"gen-1777125016-dMtvyDUzVIsV5jwtCKAG"
upstream_id
"f9ececc716174ffd80d160a8ffec6bbe"
total_cost
0.00011606
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
60.28%
Matches word count
n/a
neededClean
false
words
215
0.00%
Dialogue to Total Word Ratio
Ratio: 51.61%, Deviation: 41.61%
neededClean
false
wordsTotal
217
wordsDialogue
112
30.1376%