NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-10-01M25DYV56V5M1P4NAB63M26B6
Run Details
Model:
DeepSeek V4.1 Flash (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
26.7s
Cost:
$0.004228
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 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 peeled a banana and studied the birthday banner through binoculars. "Bill, the drop is at three, after cake. Parents wipe frosting. We grab gifts and stroll out as caterers." Bill adjusted his bow tie and frowned at the bouncy castle. "I still say clowns blend better." "Clowns draw attention. Caterers are invisible." Molly tossed the peel into a hedge and checked her clipboard. Bill unzipped a duffel bag filled with collapsed gift boxes. "And the kids? They'll scream if we take their presents." "That's why we brought candy. Toss it, they scramble, we snatch." Bill nodded slowly, his clown wig slipping. "What if a parent asks about the sack of toys?" "We say it's lost and found. Then cry a little." "And no crying, either." "We cry. It works." Bill checked his watch. "Cake at three. Escape at three-oh-five." Molly produced a whistle and a fake mustache. "No balloon animals." Bill sighed. "One poodle. That's all I ask." Molly stared him down. "No poodles. We're professionals." Outside, a piñata swayed in the heat like a papier-mâché witness. Molly grinned. Bill groaned. Bill zipped the bag. The bouncy castle wheezed. Somewhere inside, a toddler began screaming about a missing cupcake.
created_at
"2026-09-10T10:31:33.295Z"
9/10/2026, 10:31:33 AM
model
"deepseek/deepseek-v4.1-flash-20260910"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
941
moderation_latency
(null)
generation_time
26703
tokens_prompt
75
tokens_completion
6113
native_tokens_prompt
93
native_tokens_completion
7024
native_tokens_completion_images
(null)
native_tokens_reasoning
6726
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
0.00422835
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1789036293-GKBHOwfICXaKHNjKkhYp"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1789036293-4vIj3T1JrlX7ZxS9tdDF"
upstream_id
"bd5fcdc2-32a3-4bc3-8b88-4e5b855cd220"
provider_responses
0
endpoint_id
"fd104bc8-535a-4d31-a847-a8e402e86a02"
id
"bd5fcdc2-32a3-4bc3-8b88-4e5b855cd220"
is_byok
false
latency
333
model_permaslug
"deepseek/deepseek-v4.1-flash-20260910"
provider_name
"DeepSeek"
status
200
total_cost
0.00422835
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: 49.75%, Deviation: 0.25%
neededClean
false
wordsTotal
203
wordsDialogue
101
100.0000%