NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2EGHGD96B13NERNJ83V1AA
Run Details
Model:
DeepSeek V4 Flash (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
3m 6s
Cost:
$0.000116
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
97.63%
Matches word count
(details)
99.97%
Dialogue to Total Word Ratio
(details)
98.7983%
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
“I’m telling you, Bill, this is the perfect score,” Molly whispered, her eyes scanning the backyard. “Kids’ party. Unsupervised gift pile. A piñata that’s already been obliterated. What could go wrong?” “Everything,” Bill hissed, flattening himself behind a bouncy castle. “We’re grown adults. We don’t fit under the snack table. And I’ve got a bad knee.” “So you’ll be the lookout. I’ll do the heavy lifting. Watch for the birthday boy’s mother—she’s the one with the screech-laugh and the wine glass glued to her hand.” “And the clown. Don’t forget the clown. He’s making balloon animals. That’s manual dexterity. He could snatch us right up.” “Clowns are notoriously non-confrontational. They’re pacifists. It’s in the union handbook.” Bill groaned. “We don’t even know what’s in the presents. Could be socks. Or board games. We’re risking felony larceny for Connect Four.” “It’s the thrill, Bill. The thrill of a loose-wrapped box and a distracted parent. Now, on my signal, we crawl. Stay low. Stay quiet. And for the love of God, if you sneeze, do it into a party favor.” “I hate you so much.” “Love you too. Now move—here comes the magician.”
created_at
"2026-04-25T13:50:49.874Z"
4/25/2026, 1:50:49 PM
model
"deepseek/deepseek-v4-flash-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1097
moderation_latency
(null)
generation_time
186200
tokens_prompt
77
tokens_completion
397
native_tokens_prompt
67
native_tokens_completion
379
native_tokens_completion_images
(null)
native_tokens_reasoning
62
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
0.0001155
router
(null)
provider_responses
0
endpoint_id
"934a69f9-bd54-474b-beca-24560f721e12"
id
"b457c8f5790541f898d83c338a6654b7"
is_byok
false
latency
45
model_permaslug
"deepseek/deepseek-v4-flash-20260423"
provider_name
"DeepInfra"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777125049-FAvVBZZ1X9M9AhHz3lnh"
session_id
(null)
api_type
"completions"
id
"gen-1777125049-0gbF92Y7bP71qDtaK9nE"
upstream_id
"b457c8f5790541f898d83c338a6654b7"
total_cost
0.0001155
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
97.63%
Matches word count
n/a
neededClean
false
words
193
99.97%
Dialogue to Total Word Ratio
Ratio: 91.33%, Deviation: 1.33%
neededClean
false
wordsTotal
196
wordsDialogue
179
98.7983%