NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2HKEC7W85SK24J2SGCAA8Q
Run Details
Model:
DeepSeek V4 Flash
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
15.2s
Cost:
$0.000102
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
97.63%
Matches word count
(details)
96.68%
Dialogue to Total Word Ratio
(details)
97.1551%
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
“You sure this is the right house? The one with the inflatable unicorn?” Molly squinted at the rainbow banner. “Unicorn, three bouncy castles, and a piñata shaped like a llama. It’s definitely the one,” Bill said, adjusting his fake mustache. “And our cover is… balloon artists?” “We’re the Balloon Bandits. I printed cards.” “Cards. We’re printing cards now? For a job?” “It’s a party, Moll. You can’t just lurk. You need a bit of shtick.” “I don’t do shtick. I do silent and grabby.” “Then grab a balloon. I’ll handle the parents while you vacuum up the gift table. Think you can handle a room of sugared-up six-year-olds?” “I’ve handled worse. Remember the retirement home gig? That one lady bit me.” “And we got out with three jars of gummy bears. Look, the key is the stacking. The presents are all in those shiny bags for a reason. They’ll stack like Tetris blocks.” “Or a Jenga tower.” “Don’t Jenga my heist. We’re in and out. I’ll do a balloon giraffe, you make the swap with the dummy boxes. Easy.” “And if the birthday kid cries?” “Dollar store whistle. Distract with noise. They’re basically squirrels.” “Fine. But if that unicorn deflates, I’m leaving you with the squeaky giraffe.”
created_at
"2026-04-25T14:44:50.699Z"
4/25/2026, 2:44:50 PM
model
"deepseek/deepseek-v4-flash-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
716
moderation_latency
(null)
generation_time
4983
tokens_prompt
77
tokens_completion
358
native_tokens_prompt
67
native_tokens_completion
329
native_tokens_completion_images
(null)
native_tokens_reasoning
0
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
0.0001015
router
(null)
provider_responses
0
endpoint_id
"934a69f9-bd54-474b-beca-24560f721e12"
is_byok
false
latency
44
model_permaslug
"deepseek/deepseek-v4-flash-20260423"
provider_name
"DeepInfra"
status
(null)
1
endpoint_id
"722e0746-2034-4d6e-a08f-e6271849ee9e"
id
"00b6e615-07fd-48ec-b85c-054cd97a195c"
is_byok
false
latency
277
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-1777128290-6wDtFYb8vRpjHi5uHKIM"
session_id
(null)
api_type
"completions"
id
"gen-1777128290-c1MZpzbJLDtDdH5vDwZa"
upstream_id
"00b6e615-07fd-48ec-b85c-054cd97a195c"
total_cost
0.0001015
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepSeek"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
97.63%
Matches word count
n/a
neededClean
false
words
207
96.68%
Dialogue to Total Word Ratio
Ratio: 94.29%, Deviation: 4.29%
neededClean
false
wordsTotal
210
wordsDialogue
198
97.1551%