NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2EXXJG2R5NAJKBGMHCD4XY
Run Details
Model:
DeepSeek V4 Pro (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
5m 23s
Cost:
$0.010525
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
99.94%
Dialogue to Total Word Ratio
(details)
99.9597%
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 wiped a smudge of greasepaint from her cheek and squinted through the candy-cane-striped binoculars. The target was a pastel-colored house groaning under the weight of crepe paper and parental anxiety. A banner flapped in the breeze: “Happy 5th Birthday, Oliver!” Beneath it, a trestle table sagged with loot—flat-screen-sized boxes wrapped in dinosaurs, glittering bags of unknown treasure, and a suspiciously teapot-shaped parcel that Molly coveted. Bill cracked his knuckles inside his furry bear costume, the headpiece tucked under his arm like a severed mascot. He had a juice box in one hand and a lockpick disguised as a party blower in the other. “Piñata’s gift cards,” Molly said. “I’ll be the magician’s assistant,” Bill replied, his voice muffled by the bear head when he jammed it on. “The clown?” she asked, nodding toward a man on stilts. “Allergic to cats. Brought a tabby.” Bill unzipped a gym bag revealing a sleepy orange cat wearing a tiny party hat. “We go at cake,” Molly decided, checking her watch. The birthday song had started, a discordant wail of small children. Molly slipped a whoopee cushion into her back pocket. Bill fed the tabby, nodding slowly. The sugar-fueled chaos was nigh.
created_at
"2026-04-25T13:58:09.635Z"
4/25/2026, 1:58:09 PM
model
"deepseek/deepseek-v4-pro-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
925
moderation_latency
(null)
generation_time
321546
tokens_prompt
77
tokens_completion
9844
native_tokens_prompt
67
native_tokens_completion
12064
native_tokens_completion_images
(null)
native_tokens_reasoning
11765
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
0.010524825
router
(null)
provider_responses
0
endpoint_id
"d084170b-dd99-4e53-9ae1-b63881f3cfbf"
id
"8b5b0925-b744-4608-bcfe-00f58c7be7a5"
is_byok
false
latency
268
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-1777125489-QmLAxlUJkNsoR36z2gwB"
session_id
(null)
api_type
"completions"
id
"gen-1777125489-bXKuwyGLTSk9tTla4QeB"
upstream_id
"8b5b0925-b744-4608-bcfe-00f58c7be7a5"
total_cost
0.010524825
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepSeek"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.98%
Matches word count
n/a
neededClean
false
words
202
99.94%
Dialogue to Total Word Ratio
Ratio: 11.59%, Deviation: 1.59%
neededClean
false
wordsTotal
207
wordsDialogue
24
99.9597%