NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2HKQ48V8TENFDNEBDP92J8
Run Details
Model:
DeepSeek V4 Pro (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
14.5s
Cost:
$0.000415
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
95.99%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
66.3873%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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
"Bill, you want to infiltrate a seven-year-old's unicorn-themed birthday party. For a pile of glitter-encrusted plastic." "Correction, Molly. For a pile of glitter-encrusted plastic containing at least three gift cards and a brand-new tablet. I peeked at the gift table during setup. Operation Sugar Rush is a go." "You peeked? Your reconnaissance was pretending to be a balloon artist. You made a poodle that looked like a depressed sausage." "The children were too critical. That's beside the point. The point is the cake. The giant, papier-mâché unicorn cake. It's hollow." "You want to hide inside a fake cake?" "I want *you* to hide inside the fake cake. You're more compact. When they sing 'Happy Birthday,' you burst out, create a diversion with the leftover depressed sausage balloons, and grab the haul." "And what will you be doing, el capitan?" "I'll be the party entertainer, 'Magic Blaine.' I'll mesmerize them by pulling a never-ending handkerchief chain from my sleeve. It's a thirty-foot rainbow. By the time I'm done, their tiny brains will be mush." "Mush is right. They'll stampede you. You're allergic to joy and have the sleight of hand of a cement mixer." "That's part of my roguish charm. Now, can you fit in the cake or not?"
created_at
"2026-04-25T14:44:59.661Z"
4/25/2026, 2:44:59 PM
model
"deepseek/deepseek-v4-pro-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1243
moderation_latency
(null)
generation_time
14475
tokens_prompt
77
tokens_completion
492
native_tokens_prompt
67
native_tokens_completion
443
native_tokens_completion_images
(null)
native_tokens_reasoning
147
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
0.000414555
router
(null)
provider_responses
0
endpoint_id
"d084170b-dd99-4e53-9ae1-b63881f3cfbf"
id
"a4501a6a-e689-4b25-87f4-f7373be0bd25"
is_byok
false
latency
310
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-1777128299-c51o4vxfSU96GVlGTIpx"
session_id
(null)
api_type
"completions"
id
"gen-1777128299-853AICeiKV9SOZ9VyHum"
upstream_id
"a4501a6a-e689-4b25-87f4-f7373be0bd25"
total_cost
0.000414555
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepSeek"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
95.99%
Matches word count
n/a
neededClean
false
words
208
36.79%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
217
wordsDialogue
217
66.3873%