NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-20-01M5C6MMT5FDFAY6A4WP5QNT0M
Run Details
Model:
DeepSeek V4.1 Flash 1017 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
24.4s
Cost:
$0.002117
Provider:
InferenceNet
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
72.27%
Dialogue to Total Word Ratio
(details)
86.1350%
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
Molly tapped the crayon map. "Okay, Bill, the clown’s distraction lasts four minutes. You grab the presents; I handle the cake table." "Four minutes? Molly, last time you said four minutes, I spent three of them stuck in a ball pit." "That ball pit was not on the blueprint." "It was shaped like a dinosaur, Molly. There were warning signs." "Fine. New plan: you go in as the magician’s assistant. No one questions a man in a rabbit suit." "I’m not wearing the rabbit suit. The ears squeak." "The squeaking is tactical. It covers the alarm." "What alarm? It’s a birthday party for a six-year-old." "Exactly. Six-year-olds have ruthless security. Party bags, Bill. Party bags." "Okay, but we only take the good presents. No socks." "Obviously. We’re professionals, not monsters." "What about the birthday boy?" "He gets a decoy gift. A lovely card. Signed from the clown." "The clown is our getaway driver." "See? Synergy." "And if a kid asks for a balloon animal?" "You make a sword. Kids love swords." "Can we avoid felonies involving balloon swords?" "Bill, focus. Presents first, moral crisis later." "Fine. But if I hear Happy Birthday sung one more time, I’m keeping the cake."
created_at
"2026-10-20T08:25:25.579Z"
10/20/2026, 8:25:25 AM
model
"deepseek/deepseek-v4.1-flash-20261017"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
175
moderation_latency
(null)
generation_time
24418
tokens_prompt
75
tokens_completion
4087
native_tokens_prompt
67
native_tokens_completion
4224
native_tokens_completion_images
(null)
native_tokens_reasoning
3934
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
0.00211736
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1792484725-ECQD8UqYYEjfEDXV7f1y"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1792484725-2h1zRbbd8w3YcvTyj3cI"
upstream_id
"gv2_v27I9a0s8fB9JyjgjHbLW"
provider_responses
0
endpoint_id
"4231aea9-73af-4a2f-bd14-660b1d8b13b2"
id
"gv2_v27I9a0s8fB9JyjgjHbLW"
is_byok
false
latency
175
model_permaslug
"deepseek/deepseek-v4.1-flash-20261017"
provider_name
"InferenceNet"
status
200
total_cost
0.00211736
cache_discount
(null)
upstream_inference_cost
0
provider_name
"InferenceNet"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
72.27%
Dialogue to Total Word Ratio
Ratio: 97.55%, Deviation: 7.55%
neededClean
false
wordsTotal
204
wordsDialogue
199
86.1350%