NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2FZ5NXQXV3NFGRQKR0XPEV
Run Details
Model:
DeepSeek V4 Pro (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
4m 15s
Cost:
$0.008660
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 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 and Bill crouched behind the inflatable birthday castle, its garish turrets quivering with the shrieks of tiny guests. Bill unfolded a glitter-encrusted napkin map, tracing a crayon X over the colossal present pile with a finger. “We slide in during the magic finale.” Molly nodded, adjusting her lopsided fairy wings, one of which kept poking Bill in the eye. “When the rabbit vanishes, we strike.” A juice box exploded nearby, and they flinched, the sticky spray misting their disguises. The smell of orange concentrate and desperation hung thick. Bill produced a whoopee cushion from the folds of his pink tutu with misplaced pride. “First, the decoy.” He placed it carefully on a miniature chair, then stepped back to admire his handiwork. Molly checked the escape route: a crawl through the bouncy castle’s intestines, a dash past the face-painting station, and into a van disguised as an ice cream truck. The presents, a shimmering mountain of glossy paper and elaborate bows, sat unguarded beneath a piñata shaped like a smug unicorn. “Now? Pull the cord?” Bill grinned, patting a pair of gleaming pliers. Somewhere beyond the ball pit, a clown began to sob in a key of defeat. Perfect timing.
created_at
"2026-04-25T14:16:17.857Z"
4/25/2026, 2:16:17 PM
model
"deepseek/deepseek-v4-pro-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
948
moderation_latency
(null)
generation_time
254608
tokens_prompt
77
tokens_completion
8761
native_tokens_prompt
67
native_tokens_completion
9920
native_tokens_completion_images
(null)
native_tokens_reasoning
9641
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
0.008659545
router
(null)
provider_responses
0
endpoint_id
"d084170b-dd99-4e53-9ae1-b63881f3cfbf"
id
"1142c69b-9507-4147-b988-077aa4b3e6ae"
is_byok
false
latency
288
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-1777126577-idZRQ8WA9WypMiHQjJeP"
session_id
(null)
api_type
"completions"
id
"gen-1777126577-fN0LBDGATGqXsGgLyT8c"
upstream_id
"1142c69b-9507-4147-b988-077aa4b3e6ae"
total_cost
0.008659545
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: 9.90%, Deviation: 0.10%
neededClean
false
wordsTotal
202
wordsDialogue
20
100.0000%