NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1KC285B1GARFPY5MZC190AQ
Run Details
Model:
DeepSeek V4 Pro 0813 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
7.1s
Cost:
$0.001312
Provider:
Together
Evaluation summary
Score
Evaluator
Details Link
20.19%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
60.0946%
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 we just walk in?" Molly asked, licking frosting off her finger from a stolen cupcake. "Walk in? No. We *arrive*," Bill said, adjusting a clip-on bow tie. "I'm the magician. You're the balloon lady." "I can't make balloon animals." "Neither can half the clowns in this city. You just twist until something pops and yell 'ta-da.'" "And the presents?" "Table by the bouncy castle. Parents stack them like idiots. We wait for the piñata. Every kid turns around, I do a card trick, you load the wagon." "What wagon?" "The one I'm stealing from the garden center next door. It's got little plastic flowers on it. Very festive." "You want to wheel a wagon full of stolen birthday gifts through a yard full of mothers?" "Not through. Around. While they're blindfolded and swinging a stick at a donkey." "That's the piñata, Bill." "Exactly. Chaos. We slip out the side gate. I'll honk a horn and yell 'surprise.'" "Whose horn?" "The clown's. I'm also stealing his shoes." "You're going to get us arrested." "Only if the pony bites me again."
created_at
"2026-09-03T10:12:07.993Z"
9/3/2026, 10:12:07 AM
model
"deepseek/deepseek-v4-pro-20260813"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
605
moderation_latency
(null)
generation_time
7078
tokens_prompt
75
tokens_completion
321
native_tokens_prompt
67
native_tokens_completion
309
native_tokens_completion_images
(null)
native_tokens_reasoning
44
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"
service_tier
(null)
usage
0.00131208
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788430327-holqS7zuE7nOJGALWi0y"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788430327-AQHwgINuAZHM9zr3A2bl"
upstream_id
"1c12bcd5-aws_ue2"
provider_responses
0
endpoint_id
"218b0cec-3278-4b88-8ee0-3f346eccd35f"
id
"1c12bcd5-aws_ue2"
is_byok
false
latency
605
model_permaslug
"deepseek/deepseek-v4-pro-20260813"
provider_name
"Together"
status
200
total_cost
0.00131208
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Together"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
20.19%
Matches word count
n/a
neededClean
false
words
180
100.00%
Dialogue to Total Word Ratio
Ratio: 89.56%, Deviation: 0.44%
neededClean
false
wordsTotal
182
wordsDialogue
163
60.0946%