NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1KA9C1NT5BRRTGDC4WMZ6J1
Run Details
Model:
DeepSeek V4 Pro 0813 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
1m 35s
Cost:
$0.028598
Provider:
Parasail
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 adjusted her pink party hat and peered over the dashboard of the stolen ice cream van, which still smelled of melted bubblegum and regret. Bill licked sprinkles from his fingers and tapped the crayon-drawn map spread across the steering wheel. The target was a six-year-old's backyard birthday bash, and the presents sat unguarded beneath a folding table shaped like a unicorn. A single clown patrolled the perimeter, armed with a balloon animal and a whistle. Molly pointed at the bouncy castle. "Clown's distracted." Bill frowned. "That's a unicorn." She ignored him. He considered this and pulled a wand from his sleeve. "No one suspects a magician." Molly sighed. They had rented a rabbit, but it had chewed through the get-away balloon. Now the plan hinged on Bill's ability to pull scarves from his mouth while Molly loaded gift bags into a wagon disguised as a parade float. The clown honked in the distance. Bill asked, "Do we sing?" Molly said, "No. We juggle." She handed him three stolen oranges and a birthday candle. Bill said, "Okay. I'll juggle now." The ice cream van's jingle was stuck on a single note. Time was absolutely short. Very, very short indeed, now.
created_at
"2026-09-03T09:41:04.194Z"
9/3/2026, 9:41:04 AM
model
"deepseek/deepseek-v4-pro-20260813"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
536
moderation_latency
(null)
generation_time
94443
tokens_prompt
75
tokens_completion
6847
native_tokens_prompt
146
native_tokens_completion
7173
native_tokens_completion_images
(null)
native_tokens_reasoning
6551
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
0.0285978
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788428464-pjhibWFA1Zsc4ZA2T8tY"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788428464-6mzbZAFq2jTBpniEObOz"
upstream_id
"93fc4614d70f4d45a5e9b5599e4a8cf3"
provider_responses
0
endpoint_id
"487a0ef9-ddaa-4d3d-b882-7912daa08555"
id
"93fc4614d70f4d45a5e9b5599e4a8cf3"
is_byok
false
latency
536
model_permaslug
"deepseek/deepseek-v4-pro-20260813"
provider_name
"Parasail"
status
200
total_cost
0.0285978
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Parasail"
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: 9.80%, Deviation: 0.20%
neededClean
false
wordsTotal
204
wordsDialogue
20
100.0000%