NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2J6ZHH4AY6D28NZE8FD8CB
Run Details
Model:
DeepSeek V4 Flash
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
5.0s
Cost:
$0.000101
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
93.65%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
46.8248%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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 knelt behind a hedge, peering through binoculars at the inflatable castle bobbing in the backyard. “Okay, Bill, give me the lay of the land again.” Bill shuffled the napkin schematic, smudging the hand-drawn arrows. “Clown station at eleven o’clock. Bubble machine at two. Present pile between the bounce house and the petting zoo, guarded by a small girl who looks like she could take my kidney.” “She’s eight, Bill.” “Eight years of rage, Moll. That’s a vet. We go in from the side, I create a diversion. I’ll— what’s the word?— floss.” “You don’t know how to floss.” “I’ll wave my arms like a windmill, it’ll be fine. You snatch the gift bag with the glittery tissue.” “That’s the birthday pull. The real haul is the plastic tub under the table. It’s got the tablets.” Bill squinted. “Tablets? Like Moses?” “Gift cards, you moron. Five hundred, easy.” “Right. So I mime a seizure, you grapple the tub.” “That’s the worst plan you’ve had in three years.” “It’s three years better than your last one. Remember the alpaca?” “That was a llama, and it was your fault.” Molly sighed. “Fine. Windmill and mime. But if the kid with the unicorn horn spots us, I’m using you as a shield.”
created_at
"2026-04-25T14:55:30.869Z"
4/25/2026, 2:55:30 PM
model
"deepseek/deepseek-v4-flash-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
508
moderation_latency
(null)
generation_time
4945
tokens_prompt
77
tokens_completion
351
native_tokens_prompt
67
native_tokens_completion
327
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
0.00010094
router
(null)
provider_responses
0
endpoint_id
"722e0746-2034-4d6e-a08f-e6271849ee9e"
id
"0a412233-ccb2-4c28-a0e3-b8e1576d5625"
is_byok
false
latency
283
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-1777128930-UsrFiBgCZwFbIxo3PuSI"
session_id
(null)
api_type
"completions"
id
"gen-1777128930-JW3RdS2xfG2C6gVXAsMH"
upstream_id
"0a412233-ccb2-4c28-a0e3-b8e1576d5625"
total_cost
0.00010094
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
0.00%
Dialogue to Total Word Ratio
Ratio: 85.71%, Deviation: 35.71%
neededClean
false
wordsTotal
210
wordsDialogue
180
46.8248%