NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-20-01M5C66T6W4M50FMM59BN9EWA8
Run Details
Model:
DeepSeek V4.1 Flash 1017 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
14.2s
Cost:
$0.001028
Provider:
InferenceNet
Evaluation summary
Score
Evaluator
Details Link
99.38%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
68.0824%
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, the clown goes left at noon, the piñata distracts the herd, and we take every present." "Every present? Even the dinosaur-shaped one that makes that infernal roaring noise?" "Especially that one. Its battery compartment is big enough for a Fabergé egg." "We’re not stealing a Fabergé egg. We’re stealing a child’s birthday." "Don’t make it weird. The kid’s got forty guests and a bouncy castle. Nobody counts gifts after cake." "Last time you said nobody counts napkins. We got chased by a caterer with a ladle." "This time we wear party hats. Camouflage." "We’re two grown adults in trench coats. The hats won’t fix the vibes." "Fine. You go as the magician’s assistant. I’ll be the pony." "There’s no pony." "There is if we bring one. I know a guy." "No ponies. No eggs. We grab the pile by the snack table and exit through the ball pit." "See? That’s teamwork. Now help me inflate this decoy giraffe." "And the clown?" "He’s nearsighted. Wave a balloon animal and he’ll follow it into traffic." "Bill, that’s dark." "It’s a children’s party, Molly. Keep it whimsical." "So we’re agreed: hats, ball pit, no felony traffic incident." "Agreed. But if that giraffe squeaks, I’m blaming you."
created_at
"2026-10-20T08:17:52.557Z"
10/20/2026, 8:17:52 AM
model
"deepseek/deepseek-v4.1-flash-20261017"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
157
moderation_latency
(null)
generation_time
13936
tokens_prompt
75
tokens_completion
1901
native_tokens_prompt
67
native_tokens_completion
2046
native_tokens_completion_images
(null)
native_tokens_reasoning
1718
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
0.00102836
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1792484272-qANrpOllvyjj5ApCOFxX"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1792484272-wWrLUjwleLsBPQNJqRGm"
upstream_id
"gv2_n34O9IwHVgTGr5ZuKy7EI"
provider_responses
0
endpoint_id
"4231aea9-73af-4a2f-bd14-660b1d8b13b2"
id
"gv2_n34O9IwHVgTGr5ZuKy7EI"
is_byok
false
latency
157
model_permaslug
"deepseek/deepseek-v4.1-flash-20261017"
provider_name
"InferenceNet"
status
200
total_cost
0.00102836
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
99.38%
Matches word count
n/a
neededClean
false
words
205
36.79%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
206
wordsDialogue
206
68.0824%