NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-10-01M25DQ4P2CZ1XGSDV82ZNDPNJ
Run Details
Model:
DeepSeek V4.1 Flash (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
17.8s
Cost:
$0.002492
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 unfolded a crayon map of the Fitzwilliam birthday party while Bill sharpened a plastic fork against his belt. The fence across the street promised a quick exit, assuming the bouncy castle did not achieve liftoff. They studied the clown's patrol route, the piƱata's blind spot, and the pile of presents near the punch bowl. Molly tapped the target: a teetering stack wrapped in dinosaur paper. Bill worried about security: eight toddlers, one magician, and a grandmother who smelled like vengeance. They rehearsed their cover as exhausted parents arriving late with a decoy gift. The plan required stealth, speed, and possibly a juice box bribe. "Balloons?" Bill whispered. "Obstacles," Molly said. "Cake?" "Distraction." "Presents?" "Every last one." "Toddlers?" "Faster than they look." "Grandma?" "Bribe with bingo." "Escape?" "Ball pit." Bill nodded. Then he frowned. The clown remained an unpredictable variable, possibly armed with squirting flowers and no mercy. They would disable him with a stolen napkin and a well-aimed piece of cake. Molly checked her cracked watch, held together by glitter glue. Bill tightened his gloves, which were socks. Somewhere inside, children shrieked with joy, a sound they would convert into profit. They high-fived, missed, and blamed the balloon arch.
created_at
"2026-09-10T10:27:20.903Z"
9/10/2026, 10:27:20 AM
model
"deepseek/deepseek-v4.1-flash-20260910"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1247
moderation_latency
(null)
generation_time
17803
tokens_prompt
75
tokens_completion
3952
native_tokens_prompt
93
native_tokens_completion
4130
native_tokens_completion_images
(null)
native_tokens_reasoning
3831
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
0.00249195
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1789036040-Md2hQknpva7HMmZ4QYUk"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1789036040-VIIMmjuWsoX130DEAmxM"
upstream_id
"430469b7-4d17-40b6-a183-6bb2583ab082"
provider_responses
0
endpoint_id
"fd104bc8-535a-4d31-a847-a8e402e86a02"
id
"430469b7-4d17-40b6-a183-6bb2583ab082"
is_byok
false
latency
341
model_permaslug
"deepseek/deepseek-v4.1-flash-20260910"
provider_name
"DeepSeek"
status
200
total_cost
0.00249195
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%