NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-20-01M5C66T6X5ZRHHWF4MDBB5YD2
Run Details
Model:
DeepSeek V4.1 Flash 1017 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
12.3s
Cost:
$0.000898
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 bell above the bakery door chimed, and the scent of nutmeg and butter wrapped around the newcomer like a scarf. A tray of lemon tarts sat cooling on the counter, each crowned with a tiny sugared violet. “You’re early. The coffee’s still gurgling.” “Early is the only way to get one of those raspberry swirls before the church choir descends.” “Then you’ll want to hear this before they do. Someone borrowed my grandmother’s recipe box last night. Left the lid open, and the card for the county-fair crumb cake is gone.” “Gone? Not misplaced?” “I’ve searched every flour bin and apron pocket. It wasn’t a ghost, either—the back door was unlocked and there’s a footprint in the powdered sugar.” “That’s a bold thief.” “Or a desperate baker with a grudge against blue ribbons.” “Good heavens. Should we call the sheriff?” “Not yet. I’ve got a hunch. Whoever took it will need to bake it, and there’s only one oven in town that can caramelize the topping just right.” A beat. “Mine.” “Exactly. So, coffee first?” “Absolutely. Then we set a trap.” Outside, the church choir’s first soprano began to sing. Somewhere in the alley, a spoon clinked against a bowl.
created_at
"2026-10-20T08:17:52.599Z"
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
86
moderation_latency
(null)
generation_time
12010
tokens_prompt
78
tokens_completion
1734
native_tokens_prompt
65
native_tokens_completion
1785
native_tokens_completion_images
(null)
native_tokens_reasoning
1491
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
0.0008977
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1792484272-csVUJqpEWIYZ9x4qNNu9"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1792484272-LLyBpvZt8THjwTlYo0E0"
upstream_id
"gv2_6lq3Fv2TANeJINzw0mjvz"
provider_responses
0
endpoint_id
"4231aea9-73af-4a2f-bd14-660b1d8b13b2"
id
"gv2_6lq3Fv2TANeJINzw0mjvz"
is_byok
false
latency
86
model_permaslug
"deepseek/deepseek-v4.1-flash-20261017"
provider_name
"InferenceNet"
status
200
total_cost
0.0008977
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)