NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2DYTAWZ26JJN7JZP1QAS7F
Run Details
Model:
DeepSeek V4 Pro (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
5m 2s
Cost:
$0.010013
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 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 unfolded a glitter-speckled blueprint across the sticky picnic table. "The operation is called 'Piñata Fallout'," she said, tapping a crayon drawing of a bounce house. Bill tugged at his rented elf costume. "Why do I always have to be the elf?" "Because you have the chin for it. Now listen." She stabbed a juice box with a straw. "We enter as party entertainers. You'll twist balloons into obscene shapes to distract the parents." Bill groaned, his elf bells jingling. "What's the signal to grab the presents?" Molly pointed to a sparkly wristwatch. "When the birthday boy vomits from over-excitement, you'll hear me yodel." Bill scratched his chin. "Yodel? That's our sophisticated cue?" "We're artists, Bill. Criminals of panache." She adjusted her cake inspector badge. He sighed, jingling miserably. "And if the piñata bees don't cause enough chaos?" Molly grinned, patting a fanny pack of glitter bombs. "That's why god invented the Party Cannon." Bill stared. "You have a cannon?" "A confetti cannon retrofitted for chaos. It shoots cupcakes and regret." She mimed a dramatic explosion. Bill nodded. "Okay." His elf hat drooped. The sugar-fueled chaos of the party echoed from inside the community centre. Molly pocketed her badge, ready.
created_at
"2026-04-25T13:41:09.09Z"
4/25/2026, 1:41:09 PM
model
"deepseek/deepseek-v4-pro-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
819
moderation_latency
(null)
generation_time
302394
tokens_prompt
77
tokens_completion
8894
native_tokens_prompt
67
native_tokens_completion
11476
native_tokens_completion_images
(null)
native_tokens_reasoning
11175
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
0.010013265
router
(null)
provider_responses
0
endpoint_id
"d084170b-dd99-4e53-9ae1-b63881f3cfbf"
id
"5f3fd3cb-baaa-4edd-91d9-63f5f223fd8e"
is_byok
false
latency
285
model_permaslug
"deepseek/deepseek-v4-pro-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-1777124469-18nLF0COUBeZUvUsP23H"
session_id
(null)
api_type
"completions"
id
"gen-1777124469-KuSsv8p9VoxVKy2c425Q"
upstream_id
"5f3fd3cb-baaa-4edd-91d9-63f5f223fd8e"
total_cost
0.010013265
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepSeek"
response_cache_source_id
(null)
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: 49.75%, Deviation: 0.25%
neededClean
false
wordsTotal
203
wordsDialogue
101
100.0000%