NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-10-01M25DG2P56ACG7GWXG1689F46
Run Details
Model:
DeepSeek V4.1 Flash (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
19.9s
Cost:
$0.002905
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 the clown suit with the gravity of a bomb disposal expert. Bill studied the birthday map: pony rides, piñata, cake table, and a mountain of presents guarded by a sugar-crazed mob of seven-year-olds. "We hit during pin the tail," Bill whispered. "Or cake," Molly said. "Frosting makes them slow." Bill nodded, tightening his tiny top hat. The plan was simple. Molly would distract the parents with a magic trick involving a rabbit and a smoke bomb. Bill would creep behind the gift table, sweep every wrapped box into a duffel bag shaped like a teddy bear, then escape through the bouncy castle’s emergency flap. "Balloons?" Bill asked. "Popped," Molly replied. "Panic." They rehearsed their aliases: Uncle Fizz and Auntie Grabby. They practiced apologizing to toddlers. They debated whether stealing a scooter counted as a getaway vehicle. "Cake?" Bill added. The party playlist thumped like a tiny alarm. Somewhere a piñata cracked. Softly. Then a small voice behind them asked if they were the clowns. Molly turned. A birthday girl in a tiara held a list of guests and a whistle. Bill smiled weakly and hid the duffel behind his back. "Improvisation," Molly muttered. Bill sighed. "I hate improv."
created_at
"2026-09-10T10:23:29.481Z"
9/10/2026, 10:23:29 AM
model
"deepseek/deepseek-v4.1-flash-20260910"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1083
moderation_latency
(null)
generation_time
19812
tokens_prompt
75
tokens_completion
4315
native_tokens_prompt
93
native_tokens_completion
4819
native_tokens_completion_images
(null)
native_tokens_reasoning
4532
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
0.00290535
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1789035809-zqh4DGqAuUCb7Z7rIpzo"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1789035809-yL56uLzXYaezS7Ueewbc"
upstream_id
"57666cfb-9fce-4685-b252-63ff4600d87a"
provider_responses
0
endpoint_id
"fd104bc8-535a-4d31-a847-a8e402e86a02"
id
"57666cfb-9fce-4685-b252-63ff4600d87a"
is_byok
false
latency
453
model_permaslug
"deepseek/deepseek-v4.1-flash-20260910"
provider_name
"DeepSeek"
status
200
total_cost
0.00290535
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: 9.85%, Deviation: 0.15%
neededClean
false
wordsTotal
203
wordsDialogue
20
100.0000%