NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-10-01M25DSTHAB9TZHNSBDSSBPSZW
Run Details
Model:
DeepSeek V4.1 Flash (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
15.2s
Cost:
$0.002210
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
27.10%
Dialogue to Total Word Ratio
(details)
63.5487%
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 unfolded the crayon-smeared invitation like a bank blueprint. The party was at the Fitzwilliams' mansion, Saturday, two o'clock, featuring a petting zoo, a bouncy castle, and, according to a reliable source, a mountain of presents. Bill sharpened a plastic fork against his belt. "Approach?" Bill asked. "Clown entrance," Molly said. "Terrifying." "Exactly." They mapped the route: through the hedge maze, past the face-painter, into the gift grotto disguised as a fairy princess and a very tall toddler. Molly would distract the magician with a heckle. Bill would sweep the present table into a Santa sack while parents filmed cupcakes. The complication: thirty sugar-crazed children and one vigilant grandmother with a cane. The twins had sticky fingers and a whistle. The poodle wore a security vest. Bill hated poodles. Molly hated whistles. "She'll recognize us," Bill said. "Not if we wear party hats." "That's it?" "And cry." "And glitter." They rehearsed their innocent faces. Bill looked constipated. Molly looked like a raccoon planning arson. At two o'clock, they would waddle in, steal every wrapped box, and be gone before the piƱata cracked. The only question was whether to leave the birthday boy one gift or let him learn capitalism early.
created_at
"2026-09-10T10:28:48.814Z"
9/10/2026, 10:28:48 AM
model
"deepseek/deepseek-v4.1-flash-20260910"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1014
moderation_latency
(null)
generation_time
15165
tokens_prompt
75
tokens_completion
3543
native_tokens_prompt
93
native_tokens_completion
3660
native_tokens_completion_images
(null)
native_tokens_reasoning
3371
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
0.00220995
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1789036128-KjYXLfBqs4XrW3oWEd29"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1789036128-RCKyOUXCm07jyEMneu3X"
upstream_id
"7ed7b9c9-09f2-4563-af49-b03dc32a29e4"
provider_responses
0
endpoint_id
"fd104bc8-535a-4d31-a847-a8e402e86a02"
id
"7ed7b9c9-09f2-4563-af49-b03dc32a29e4"
is_byok
false
latency
342
model_permaslug
"deepseek/deepseek-v4.1-flash-20260910"
provider_name
"DeepSeek"
status
200
total_cost
0.00220995
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
27.10%
Dialogue to Total Word Ratio
Ratio: 20.69%, Deviation: 10.69%
neededClean
false
wordsTotal
203
wordsDialogue
42
63.5487%