NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2DP9TPWE0N4ASV6H2KFANK
Run Details
Model:
DeepSeek V4 Pro (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
10.9s
Cost:
$0.000371
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
98.46%
Dialogue to Total Word Ratio
(details)
49.2302%
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 unfolded a crayon-drawn blueprint across the sticky picnic table, her finger tracing a wobbly line that Bill assumed was a wall. A juice box lay on its side between them, slowly bleeding purple onto the map. Bill squinted at a lopsided X marking the gift table, then at a cluster of circles Molly had labelled “TINY UNPREDICTABLE DRUNKS.” “Ball pit diversion?” “Too crinkly.” He nodded, stroking his chin. Their masterstroke involved a rented pony, a clipboard, and a flawless Swedish accent. The plan hinged on exploiting the post-cake sugar crash, a narrow window of chaos Bill called the “buttercream event horizon.” Molly produced a pair of oversized sunglasses with a fake nose attached, their ticket to blending in with the five-year-old crowd. A lone balloon drifted by, startling them both. Bill grabbed it and quietly, expertly, popped it with a concealed pin, then resumed his thoughtful pose as if nothing had occurred, the tiny act of violence a meditation on the precarious nature of joy.
created_at
"2026-04-25T13:36:30.041Z"
4/25/2026, 1:36:30 PM
model
"deepseek/deepseek-v4-pro-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1051
moderation_latency
(null)
generation_time
10810
tokens_prompt
77
tokens_completion
443
native_tokens_prompt
67
native_tokens_completion
393
native_tokens_completion_images
(null)
native_tokens_reasoning
170
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
0.000371055
router
(null)
provider_responses
0
endpoint_id
"d084170b-dd99-4e53-9ae1-b63881f3cfbf"
id
"484cb0e1-0705-496f-a49b-18f55f54663f"
is_byok
false
latency
280
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-1777124190-Cwu1wh87TR31TdLrEkvu"
session_id
(null)
api_type
"completions"
id
"gen-1777124190-ylqu8meTLM4hV4PrySeI"
upstream_id
"484cb0e1-0705-496f-a49b-18f55f54663f"
total_cost
0.000371055
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepSeek"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
166
98.46%
Dialogue to Total Word Ratio
Ratio: 6.47%, Deviation: 3.53%
neededClean
false
wordsTotal
170
wordsDialogue
11
49.2302%