NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2G5SGHB1MDTB8FSDMSPAED
Run Details
Model:
DeepSeek V4 Flash (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
5.7s
Cost:
$0.000112
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.9595%
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
“You sure about this, Bill?” Molly whispered, peering through the hedge at the inflatable bounce castle. “These are kids. Like, actual tiny humans.” “Exactly,” Bill said, adjusting his fake mustache. “Children’s parties are gold mines. Parents go broke on wrapping paper alone. We walk in, smash the piñata—accidentally on purpose—and during the chaos, we pocket every gift bag.” “And what about the parents? They’re not blind.” “They’re distracted. Cake, face painting, that one kid who always cries. Timing’s everything. I’ve got the decoy: a puppet that squirts mustard.” Molly squinted. “You’re going to puppet your way past a bunch of six-year-olds?” “It’s called misdirection. I’ll be ‘Silly Splotch the Clown,’ they’ll love me. You slip around back, grab the haul. Meet by the clown car.” “We don’t have a clown car.” “I rented a lime-green Smart Car. Same difference.” Molly sighed. “And if a kid cries? Because they will.” “Then we cry too, but louder. We’re professionals, Mol.” She stared at the streamers, the balloon arch, the looming threat of juice boxes. “Fine. But if I get glitter on my new gloves, you’re buying me dinner.” “Deal. Now come on—Silly Splotch needs an audience.”
created_at
"2026-04-25T14:19:54.774Z"
4/25/2026, 2:19:54 PM
model
"deepseek/deepseek-v4-flash-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
582
moderation_latency
(null)
generation_time
5611
tokens_prompt
77
tokens_completion
409
native_tokens_prompt
67
native_tokens_completion
365
native_tokens_completion_images
(null)
native_tokens_reasoning
51
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
0.00011158
router
(null)
provider_responses
0
endpoint_id
"722e0746-2034-4d6e-a08f-e6271849ee9e"
id
"10400312-ffad-4a9a-9f6d-a612e71487d6"
is_byok
false
latency
324
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-1777126794-BLvEpFstqXLbSgYoO16L"
session_id
(null)
api_type
"completions"
id
"gen-1777126794-Ym9Yw2pWwgZLfR77y58z"
upstream_id
"10400312-ffad-4a9a-9f6d-a612e71487d6"
total_cost
0.00011158
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepSeek"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.92%
Matches word count
n/a
neededClean
false
words
197
0.00%
Dialogue to Total Word Ratio
Ratio: 82.50%, Deviation: 32.50%
neededClean
false
wordsTotal
200
wordsDialogue
165
49.9595%