NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2H0QG8N0BGV3DR0VMYX136
Run Details
Model:
DeepSeek V4 Flash (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
15.7s
Cost:
$0.000113
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
99.74%
Matches word count
(details)
90.77%
Dialogue to Total Word Ratio
(details)
95.2590%
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
“So you’re telling me,” Bill said, peering through the hedge, “we’re robbing a gaggle of five-year-olds.” “Seven-year-olds,” Molly corrected, adjusting her fake clown nose. “They’ve got better loot. Think about it—tablets, gaming consoles, the good stuff.” “I’m thinking about the screaming. The crying. The tiny, sticky fingers reaching for my pant leg.” “You’ll be in a unicorn costume, Bill. They’ll love you.” “I will not love myself. Why can’t we knock over a pharmacy like normal criminals?” “Because pharmacies don’t have wrapping paper. Look—Uncle Larry’s Magical Balloon Show starts at 2. We roll in as backup clowns. I distract the parents with balloon swords—” “While I do what? Hand out dental floss?” “You swap the gift bags with these.” She hefted a sack of empty, glitter-covered boxes. “They get a pile of junk. We get the pile of value. It’s victimless.” “Victimless?” Bill’s voice cracked. “We’re traumatizing an entire generation of birthday enthusiasts.” “They’ll learn a valuable lesson about materialism.” “They’ll learn to distrust anyone with a red nose.” “Exactly. Now get in the suit.” Bill stared at the foam horn. “I should’ve gone into banking.” “Banking doesn’t pay in Frozen dolls. Let’s move.”
created_at
"2026-04-25T14:34:37.452Z"
4/25/2026, 2:34:37 PM
model
"deepseek/deepseek-v4-flash-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
493
moderation_latency
(null)
generation_time
5508
tokens_prompt
77
tokens_completion
429
native_tokens_prompt
67
native_tokens_completion
370
native_tokens_completion_images
(null)
native_tokens_reasoning
53
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
0.00011298
router
(null)
provider_responses
0
endpoint_id
"934a69f9-bd54-474b-beca-24560f721e12"
is_byok
false
latency
54
model_permaslug
"deepseek/deepseek-v4-flash-20260423"
provider_name
"DeepInfra"
status
(null)
1
endpoint_id
"722e0746-2034-4d6e-a08f-e6271849ee9e"
id
"210d9f0e-8009-4420-9074-baeb810d99de"
is_byok
false
latency
279
model_permaslug
"deepseek/deepseek-v4-flash-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-1777127677-D2sZSkR4op0iIw3AzYo2"
session_id
(null)
api_type
"completions"
id
"gen-1777127677-DqUCKcKvqpjafAnNL5H9"
upstream_id
"210d9f0e-8009-4420-9074-baeb810d99de"
total_cost
0.00011298
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepSeek"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.74%
Matches word count
n/a
neededClean
false
words
196
90.77%
Dialogue to Total Word Ratio
Ratio: 84.42%, Deviation: 5.58%
neededClean
false
wordsTotal
199
wordsDialogue
168
95.2590%