NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2HEQDYZH3AAQ0P6YK6S5H3
Run Details
Model:
DeepSeek V4 Flash
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
14.8s
Cost:
$0.000090
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
99.38%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.6885%
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 wheezed its last breath just as Molly fixed Bill with a stare that could curdle milk. “You’re telling me the decoy is a unicycle?” Bill adjusted the rainbow clown wig on his head, its synthetic curls tickling his nose. “It’s psychological warfare. No one expects the magician to ride in on a unicycle, juggling hamsters.” “Hamsters,” Molly repeated, flat as a deflated balloon. She clicked the locking pliers in her hand, a nervous tic. “We have a five-minute window before the birthday boy’s paralytic sugar high wears off and the parents realize the piñata is full of expired coupons.” “And a real Belgian waffle iron,” Bill added, patling the stuffed unicorn backpack that held their swag. “The present pile is a goldmine. The three-year-old’s grandmother is loaded.” Molly peered through the café window at the party tent across the park. A woman in a cat-ear tiara was arguing with a man in a dinosaur costume over the correct way to blow up a balloon giraffe. “Fine. But if a single hamster escapes that juggling act, I’m using the unicycle as a blunt instrument.” Bill grinned, his teeth blindingly white against the sad rainbow fluff. “Trust the process, Mol. It’s a beautiful disaster.”
created_at
"2026-04-25T14:42:16.129Z"
4/25/2026, 2:42:16 PM
model
"deepseek/deepseek-v4-flash-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
684
moderation_latency
(null)
generation_time
4657
tokens_prompt
77
tokens_completion
330
native_tokens_prompt
67
native_tokens_completion
288
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)
num_fetches
(null)
web_search_engine
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.00009002
router
(null)
provider_responses
0
endpoint_id
"934a69f9-bd54-474b-beca-24560f721e12"
is_byok
false
latency
61
model_permaslug
"deepseek/deepseek-v4-flash-20260423"
provider_name
"DeepInfra"
status
(null)
1
endpoint_id
"722e0746-2034-4d6e-a08f-e6271849ee9e"
id
"dddeb61a-a6ba-4149-b6a5-2d629c23d1cc"
is_byok
false
latency
346
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-1777128136-rgtev1ShpRMZm6nsQ56S"
session_id
(null)
api_type
"completions"
id
"gen-1777128136-RrlA0g2L7iaH5dKTtfN4"
upstream_id
"dddeb61a-a6ba-4149-b6a5-2d629c23d1cc"
total_cost
0.00009002
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepSeek"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.38%
Matches word count
n/a
neededClean
false
words
205
0.00%
Dialogue to Total Word Ratio
Ratio: 45.93%, Deviation: 35.93%
neededClean
false
wordsTotal
209
wordsDialogue
96
49.6885%