NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-20-01M5C6G4TNSBC92QYTWQRR3Y51
Run Details
Model:
DeepSeek V4.1 Flash 1017 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
27.3s
Cost:
$0.002063
Provider:
InferenceNet
Evaluation summary
Score
Evaluator
Details Link
98.71%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.3561%
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
"Okay, Bill, walk me through it again, but pretend you're not allergic to competence," Molly said. "The clown suit gets us past security," Bill said. "I juggle, you do balloon animals, and when the piñata explodes, we swap the presents for sandbags." "Security is a nine-year-old named Trevor with a whistle." "Trevor's corrupt. I bribed him with a juice box." "That's depressing." "Capitalism is depressing. Focus. You take the left gift table, I take the right." "What about the birthday boy?" "He gets a decoy present. A lovely, empty box." "We're monsters." "We're entrepreneurs. There's cake, a magician, and forty toddlers on a sugar high. Noise covers everything." "What if the magician sees us?" "He's doing the vanishing trick. Very cooperative." "And the parents?" "Discussing quinoa. We have six minutes." "Six minutes to steal thirty presents?" "Four if I hit the piñata too hard." "Bill, if this goes wrong, I'm blaming the clown suit." "Fair. But if it goes right, we're rich and emotionally scarred." Molly tapped the table. "And if Trevor talks?" Bill shrugged. "No one believes a kid with juice on his shirt." Bill unfolded a crumpled clown map. "Agreed. Bring extra juice boxes." Molly checked her watch. "Then move. The cake's already sweating."
created_at
"2026-10-20T08:22:58.138Z"
10/20/2026, 8:22:58 AM
model
"deepseek/deepseek-v4.1-flash-20261017"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
183
moderation_latency
(null)
generation_time
27241
tokens_prompt
75
tokens_completion
3839
native_tokens_prompt
67
native_tokens_completion
4116
native_tokens_completion_images
(null)
native_tokens_reasoning
3810
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
0.00206336
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1792484578-Ipzbk6NVQ5HTeuxqtLfs"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1792484578-NGpNSA2sg35efndIEPFX"
upstream_id
"gv2_1SZOcgCXdTK0kcOrYFUUL"
provider_responses
0
endpoint_id
"4231aea9-73af-4a2f-bd14-660b1d8b13b2"
id
"gv2_1SZOcgCXdTK0kcOrYFUUL"
is_byok
false
latency
183
model_permaslug
"deepseek/deepseek-v4.1-flash-20261017"
provider_name
"InferenceNet"
status
200
total_cost
0.00206336
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
98.71%
Matches word count
n/a
neededClean
false
words
206
100.00%
Dialogue to Total Word Ratio
Ratio: 90.38%, Deviation: 0.38%
neededClean
false
wordsTotal
208
wordsDialogue
188
99.3561%