NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2DFY27ZNRZPY2NW5D5A3V7
Run Details
Model:
DeepSeek V4 Pro (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
3m 46s
Cost:
$0.009058
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.9995%
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 schemed in a sandbox shaped like a pirate ship, their mature frames a tight fit among the plastic shovels. The target was a five-year-old's treasure trove of presents, guarded by a bouncy castle and a face-painting station. Molly wore a beekeeper's veil to conceal her identity, though she claimed it was a fashionable net hat. Bill had a squirt gun filled with chocolate syrup to immobilize any adult interference. They reviewed the plan: crawl through the inflatable obstacle course, replace the presents with identical boxes of coal they'd cleverly wrapped, and escape through the cake delivery van before the clown's face-paint toxin wore off. Molly asked, "What if the clown is a cop?" Bill replied, "Our balloons are weapons." She scoffed, "That's ridiculous." He leaned in. "Exactly. Nobody suspects a thing." Her eyes narrowed. "We'll need glitter." Bill handed her a gritty tube of edible shimmer, and they shook on it, a pact sealed with sticky handprints. In the near distance, the birthday song began, and the piƱata burst open in a shower of cheap candy and tears, their cue, a perfect diversion. The children shrieked, a sound they ignored. Quietly, they crawled forth, giggling like sugar-drunk miscreants.
created_at
"2026-04-25T13:33:01.387Z"
4/25/2026, 1:33:01 PM
model
"deepseek/deepseek-v4-pro-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
939
moderation_latency
(null)
generation_time
225472
tokens_prompt
77
tokens_completion
9290
native_tokens_prompt
67
native_tokens_completion
10378
native_tokens_completion_images
(null)
native_tokens_reasoning
10098
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
0.009058005
router
(null)
provider_responses
0
endpoint_id
"d084170b-dd99-4e53-9ae1-b63881f3cfbf"
id
"ed083131-8296-465e-bc2f-99a7a3c33d7f"
is_byok
false
latency
282
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-1777123981-ols6JPxTZJ3Q4F1BLgzn"
session_id
(null)
api_type
"completions"
id
"gen-1777123981-dY7Yz8Jgq75JdTWEJZyf"
upstream_id
"ed083131-8296-465e-bc2f-99a7a3c33d7f"
total_cost
0.009058005
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
201
100.00%
Dialogue to Total Word Ratio
Ratio: 10.19%, Deviation: 0.19%
neededClean
false
wordsTotal
206
wordsDialogue
21
99.9995%