NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-10-01M25DCS0VBZN4WW8RQA6AAWFW
Run Details
Model:
DeepSeek V4.1 Flash (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
9.3s
Cost:
$0.001125
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 and Bill crouched behind the bouncy castle, surveying the backyard birthday carnage. A piƱata shaped like a donkey hung from the oak, guarded by seven toddlers on sugar rampages. Bill unrolled a crayon-drawn map. "Balloons are the alarm," Molly said. "Children are the alarm," Bill said. They studied the gift table, where wrapping paper sparkled under fairy lights. Molly adjusted her fake mustache. Bill tightened his cape. The plan required patience, timing, and perhaps a distraction involving a remote-controlled dinosaur. Unfortunately, the dinosaur was currently trapped under a beanbag chair. A clown honked nearby. Molly checked her watch, a plastic one that told time only in cartoon suns. The party mom patrolled with a juice box, dispensing justice and napkins. Bill suggested a tactical retreat to the snack table. Molly refused. They needed every present: the lumpy ones, the rattling ones, the one suspiciously shaped like a savings bond. "We need disguises," Molly whispered. "Clown suits," Bill agreed. "Presents sorted by glitter," Molly added. "Exit through cake," Bill said. Then a toddler spotted them and screamed. The heist was on, or possibly over, depending on whether the toddler accepted a bribe of cheese puffs. They ran like startled squirrels.
created_at
"2026-09-10T10:21:41.399Z"
9/10/2026, 10:21:41 AM
model
"deepseek/deepseek-v4.1-flash-20260910"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
725
moderation_latency
(null)
generation_time
9098
tokens_prompt
75
tokens_completion
1859
native_tokens_prompt
93
native_tokens_completion
1852
native_tokens_completion_images
(null)
native_tokens_reasoning
1573
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
0.00112515
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1789035701-BMe8XFvQKPzbeDaUTFxP"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1789035701-qdHYYM5q1ETJ2jMyqvX0"
upstream_id
"051a4f76-44da-47a6-a886-4f4fde151f70"
provider_responses
0
endpoint_id
"fd104bc8-535a-4d31-a847-a8e402e86a02"
id
"051a4f76-44da-47a6-a886-4f4fde151f70"
is_byok
false
latency
348
model_permaslug
"deepseek/deepseek-v4.1-flash-20260910"
provider_name
"DeepSeek"
status
200
total_cost
0.00112515
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: 9.90%, Deviation: 0.10%
neededClean
false
wordsTotal
202
wordsDialogue
20
100.0000%