NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-10-01M25DTC35RFH8NJVCYVRD3C73
Run Details
Model:
DeepSeek V4.1 Flash (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
23.3s
Cost:
$0.003474
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
100.0000%
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
Molly parted the hedge with a gloved hand and studied the backyard. A clown honked a horn. Eight toddlers shrieked near a folding table stacked with wrapped loot. Bill adjusted his dinosaur mask, which was for camouflage and, he insisted, dignity. The piñata hung like a papier-mâché moon. Bouncy castle wheezed. A mother wielded a juice box like a sidearm. Behind the grill, a golden retriever guarded a stack of hot dog buns with religious devotion, while the sprinklers hissed a warning. "Balloon arch perimeter," Molly whispered. "Kids are alarms," Bill said. "Presents by the castle." "No cake." "Sidestep the sugar and the twins, Molly, please," Bill said. Bill nodded. Their plan was simple: crawl through the petting zoo, distract the magician with a rubber chicken, snip the ribbon, and drag the gift pile into the recycling bin. Molly checked her clipboard. Bill checked his pockets for zip ties, glitter, and emergency earplugs. A toddler pointed at them and screamed, not in alarm, but because his cupcake had fallen. They froze. The clown turned. A kazoo began the theme from Mission: Impossible. This was either the perfect moment or the worst birthday ever. Molly smiled. Bill whimpered. They finally moved.
created_at
"2026-09-10T10:29:06.795Z"
9/10/2026, 10:29:06 AM
model
"deepseek/deepseek-v4.1-flash-20260910"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
814
moderation_latency
(null)
generation_time
23287
tokens_prompt
75
tokens_completion
5162
native_tokens_prompt
93
native_tokens_completion
5767
native_tokens_completion_images
(null)
native_tokens_reasoning
5485
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"
service_tier
(null)
usage
0.00347415
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1789036146-UuH2N30R9ZeP6vmPXC6E"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1789036146-Nzg74W0pOCd9SAsb9nMG"
upstream_id
"b76bf695-886c-4544-af24-983837d23ea9"
provider_responses
0
endpoint_id
"fd104bc8-535a-4d31-a847-a8e402e86a02"
id
"b76bf695-886c-4544-af24-983837d23ea9"
is_byok
false
latency
336
model_permaslug
"deepseek/deepseek-v4.1-flash-20260910"
provider_name
"DeepSeek"
status
200
total_cost
0.00347415
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepSeek"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
100.00%
Dialogue to Total Word Ratio
Ratio: 9.95%, Deviation: 0.05%
neededClean
false
wordsTotal
201
wordsDialogue
20
100.0000%