NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2E9QB30FC6W6D72J2D75E8
Run Details
Model:
DeepSeek V4 Flash
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
5.8s
Cost:
$0.000102
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
93.65%
Matches word count
(details)
86.96%
Dialogue to Total Word Ratio
(details)
90.3053%
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
“We’re really doing this?” Bill whispered, crouched behind a bouncy castle shaped like a grinning unicorn. “Stealing from a bunch of seven-year-olds?” “It’s not from them, it’s from the parents,” Molly said, tightening the straps on her inflatable giraffe costume. “They’re the ones who bought the gift cards and the tablets. The kids just get the boxes.” “I feel like a monster.” “You feel like a monster in a giraffe suit? Great. That’s the cover. When I say ‘the cake is coming,’ you cut the power to the disco lights. I grab the presents from under the Smurf tablecloth.” “What if a kid sees me?” “Then you dance. Giraffes dance at parties. It’s a known fact.” “It is not a known fact.” “It is now. You’re ‘Jeremy the Giraffe.’ I’m ‘Penelope the Penguin.’ We’re from Party Pirates, Inc. They hired us.” “They hired a DJ named Dave.” “Dave just got food poisoning from the mini quiches. I saw him sneeze in the bouncy castle. He’s out. We’re in.” Bill sighed, his neck ruff fluttering. “And the loot?” “Fifty-fifty, after I deduct costume rental and emotional damage.” “Emotional damage?” “Yeah. Listening to you whine.” Molly zipped up her penguin beak. “Now get ready. The limbo music stopped. That’s our cue.”
created_at
"2026-04-25T13:47:06.471Z"
4/25/2026, 1:47:06 PM
model
"deepseek/deepseek-v4-flash-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1268
moderation_latency
(null)
generation_time
5717
tokens_prompt
77
tokens_completion
366
native_tokens_prompt
67
native_tokens_completion
331
native_tokens_completion_images
(null)
native_tokens_reasoning
0
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"
usage
0.00010206
router
(null)
provider_responses
0
endpoint_id
"722e0746-2034-4d6e-a08f-e6271849ee9e"
id
"fdc063bc-4dab-49de-b80f-82c6c116592c"
is_byok
false
latency
414
model_permaslug
"deepseek/deepseek-v4-flash-20260423"
provider_name
"DeepSeek"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777124826-i6AOrAqnOF2ITCI9KwUg"
session_id
(null)
api_type
"completions"
id
"gen-1777124826-C3wtOD8eb2VUWNJCWXxj"
upstream_id
"fdc063bc-4dab-49de-b80f-82c6c116592c"
total_cost
0.00010206
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepSeek"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
93.65%
Matches word count
n/a
neededClean
false
words
209
86.96%
Dialogue to Total Word Ratio
Ratio: 83.89%, Deviation: 6.11%
neededClean
false
wordsTotal
211
wordsDialogue
177
90.3053%