NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-10-01M25DRTFF7YZCHQHTB5G4WDQ1
Run Details
Model:
DeepSeek V4.1 Flash (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
16.3s
Cost:
$0.002703
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
68.3940%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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, the clown suit is non-negotiable." "Fine, Bill, but I'm not wearing the squeaky shoes. They announce us like a mall cop hiccuping." "The squeaky shoes are the distraction. While I juggle, you swipe the presents." "Juggle what? Last time you juggled eggs, we spent an hour hiding yolk footprints." "This time it's beanbags. Soft. Quiet. Thematic." "Theme? We're robbing a six-year-old's birthday party." "Exactly. Pirates. Princesses. Presents. We blend in." "Blend in? You're forty-seven and bald. You look like a tax auditor with a treasure map." "I'll wear the eye patch." "Then you can't see the getaway route. There's a bouncy castle, a face painter, twelve sugar-crazed kids." "Kids are slow. We're professionals." "We're petty thieves who once got trapped in a revolving door." "That was team-building. Now listen. I distract with balloon animals. You sneak gifts to the van." "What about the parents?" "Tell them we're from the gift registry." "Do they have a gift registry?" "They have cake. We have nerve. Move, Molly." "Wait. What if the birthday kid recognizes us?" "From where? The police lineup?" "From last week's party. I gave him a fake mustache and stole his cake." "Then we wear different mustaches. Problem solved."
created_at
"2026-09-10T10:28:15.988Z"
9/10/2026, 10:28:15 AM
model
"deepseek/deepseek-v4.1-flash-20260910"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
492
moderation_latency
(null)
generation_time
16272
tokens_prompt
75
tokens_completion
4133
native_tokens_prompt
93
native_tokens_completion
4482
native_tokens_completion_images
(null)
native_tokens_reasoning
4174
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
0.00270315
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1789036095-DnmIoRGjalDuDbCQ3zTd"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1789036095-ZG8J0RIwkzK8RTS0FWTo"
upstream_id
"7f5eabd3-52e2-4744-a208-1f9fdf2e066b"
provider_responses
0
endpoint_id
"fd104bc8-535a-4d31-a847-a8e402e86a02"
id
"7f5eabd3-52e2-4744-a208-1f9fdf2e066b"
is_byok
false
latency
323
model_permaslug
"deepseek/deepseek-v4.1-flash-20260910"
provider_name
"DeepSeek"
status
200
total_cost
0.00270315
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
36.79%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
206
wordsDialogue
206
68.3940%