NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-20-01M5C6KSCTH9S3HV7JC5YGX2MX
Run Details
Model:
DeepSeek V4.1 Flash 1017 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
16.3s
Cost:
$0.001090
Provider:
InferenceNet
Evaluation summary
Score
Evaluator
Details Link
100.00%
Count dialogue tags
(details)
Model input
User/Human
You are an expert novel writer in the cozy mystery genre. Write a scene of about 200 words, with dialogue between two characters. The dialogue should be unattributed, meaning the speaker is not explicitly mentioned. The scene should be set in a small town bakery. Only return the story, nothing else.
Model response
Messages
Meta
AI
The bakery smelled of cinnamon and warm yeast, and the morning had barely cracked the windows. A tray rattled behind the counter. “The oven’s been warm since five, and someone left the back door unlatched.” “Unlatched, or politely opened?” “Don’t you start. My cinnamon rolls are accounted for, but Tuesday’s page is missing from the ledger.” “Tuesday we sold forty-two scones and one very suspicious meat pie.” “That pie was for the church fundraiser.” “And the page?” “Under the flour bin. With a thumbprint in raspberry jam.” “Raspberry? We haven’t made raspberry since June.” “Exactly. So either the ghost of summer is shoplifting recipes, or someone wants us to think the thief got sticky.” “Could be the new delivery boy. He whistles off-key and won’t go near the flour bin.” “He brought a crate of raspberries this morning. Called it a gift.” “Then we lock the back door, count the scones twice, and ask why a gift came with a missing page.” Outside, the town clock struck seven, a little too innocently. “And if that rolling pin is for the delivery boy, I’m calling the constable.” “Cozy. Very cozy. Hand it over.”
created_at
"2026-10-20T08:24:57.505Z"
10/20/2026, 8:24:57 AM
model
"deepseek/deepseek-v4.1-flash-20261017"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
176
moderation_latency
(null)
generation_time
16291
tokens_prompt
78
tokens_completion
2378
native_tokens_prompt
65
native_tokens_completion
2170
native_tokens_completion_images
(null)
native_tokens_reasoning
1895
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
0.0010902
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1792484697-9KiUfI3wrIsLZCcV7OxF"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1792484697-VSQfbBSweBBJi6us2OJm"
upstream_id
"gv2_gcFyh5LYnu3yYrBwxDfRW"
provider_responses
0
endpoint_id
"4231aea9-73af-4a2f-bd14-660b1d8b13b2"
id
"gv2_gcFyh5LYnu3yYrBwxDfRW"
is_byok
false
latency
176
model_permaslug
"deepseek/deepseek-v4.1-flash-20261017"
provider_name
"InferenceNet"
status
200
total_cost
0.0010902
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%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)