NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2DYYDMJR03N04V2KC13BKD
Run Details
Model:
DeepSeek V4 Flash (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
5.4s
Cost:
$0.000111
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
95.99%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
47.9934%
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 flattened the party invitation against the grimy wall with her thumb. “We hit the bounce house at fourteen hundred, just as the magician starts his sad balloon animals.” Bill grunted, adjusting his skeleton costume. “And the presents?” “Under the piñata. They always stack them under the piñata, like it’s a sacred shrine to disappointment.” She pulled a lollipop from her pocket and unwrapped it with her teeth. “Step one: I create a diversion. I’ll pretend to be a very enthusiastic grandmother.” “You’re thirty-two.” “I’m method. Step two: you emerge from the cake.” Bill stared at the soggy sheet cake diagram she’d drawn on a napkin. “The cake is a prop. It’s cardboard. I can’t fit in cardboard.” “You’ll fit. I measured your ribs against a photo of a Dora the Explorer cake. You’ll be fine if you don’t breathe.” He sighed, a long defeated wheeze. “And when the parents start screaming?” Molly bit her lollipop with a sharp crack. “We run. We run like we stole something, because we will have. But first, we smile. They never suspect smiling thieves.” She grinned, sugar on her teeth. “Especially at a child’s party.”
created_at
"2026-04-25T13:41:13.272Z"
4/25/2026, 1:41:13 PM
model
"deepseek/deepseek-v4-flash-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
547
moderation_latency
(null)
generation_time
5235
tokens_prompt
77
tokens_completion
397
native_tokens_prompt
67
native_tokens_completion
362
native_tokens_completion_images
(null)
native_tokens_reasoning
76
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
0.00011074
router
(null)
provider_responses
0
endpoint_id
"722e0746-2034-4d6e-a08f-e6271849ee9e"
id
"a84d11cc-fa15-4822-9c1f-f523172fe285"
is_byok
false
latency
275
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-1777124473-IU5rOEQiXihJ0UFA1vTk"
session_id
(null)
api_type
"completions"
id
"gen-1777124473-SRQuha56WXkLPPVQrSN2"
upstream_id
"a84d11cc-fa15-4822-9c1f-f523172fe285"
total_cost
0.00011074
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepSeek"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
95.99%
Matches word count
n/a
neededClean
false
words
192
0.00%
Dialogue to Total Word Ratio
Ratio: 66.84%, Deviation: 56.84%
neededClean
false
wordsTotal
193
wordsDialogue
129
47.9934%