NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2GJSGHYRFA72XN5VCACBK3
Run Details
Model:
DeepSeek V4 Pro (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
20.6s
Cost:
$0.000450
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
68.10%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
34.0511%
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 peered through the chain-link fence at the bounce castle quaking with tiny, screeching bodies. “There’s enough pink wrapping paper in that pinata-strewn nightmare to fund our retirement,” she whispered. Bill, squashed beside her in the hedge, licked cupcake frosting off a stolen napkin. “Retirement is a beach in a non-extradition country. What’s the angle? Naptime ambush?” “Better: clown car extraction. I sourced a tiny fire truck.” She spat out a leaf. “You pop out, honk the horn, they swarm for lollipops, I bag the loot.” “Honking is my love language, but kids are feral bloodhounds for sugar. Lose the lollipops. I’ll deploy a magic trick. The old vanishing-quarter-behind-the-ear, except the quarter is a smoke bomb, and the ear is the birthday boy’s corrupt little soul.” “Too theatrical. We go in as the emergency entertainment: Captain Confetti and Sprinkles the Safety Clown.” She flicked a beetle off his collar. “You’re Sprinkles. You announce a mandatory present inspection for glitter bombs. I’ll load the wagon.” Bill sighed. “I despise clown shoes. My arches will never forgive you. Do we at least get to keep the fire truck?”
created_at
"2026-04-25T14:27:06.243Z"
4/25/2026, 2:27:06 PM
model
"deepseek/deepseek-v4-pro-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
881
moderation_latency
(null)
generation_time
15091
tokens_prompt
77
tokens_completion
539
native_tokens_prompt
67
native_tokens_completion
484
native_tokens_completion_images
(null)
native_tokens_reasoning
199
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
0.000450225
router
(null)
provider_responses
0
endpoint_id
"d084170b-dd99-4e53-9ae1-b63881f3cfbf"
id
"230cb9f1-998f-4743-a974-f8e879e52db8"
is_byok
false
latency
278
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-1777127226-7Nidy19EVUEqypjEgvTZ"
session_id
(null)
api_type
"completions"
id
"gen-1777127226-VhhKh9jOmURkkohBrqez"
upstream_id
"230cb9f1-998f-4743-a974-f8e879e52db8"
total_cost
0.000450225
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepSeek"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
68.10%
Matches word count
n/a
neededClean
false
words
186
0.00%
Dialogue to Total Word Ratio
Ratio: 76.17%, Deviation: 26.17%
neededClean
false
wordsTotal
193
wordsDialogue
147
34.0511%