NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1KAT5AXVG81F9CJ928J79TP
Run Details
Model:
DeepSeek V4 Flash 0731 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
43.0s
Cost:
$0.001370
Provider:
Mancer 2
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 door jangled, and the smell of burnt sugar clung to the air. "You know, that raspberry tart you made for Mrs. Higgins’ bridge club? I heard it wasn't the raspberries that made her feel funny." A flour-dusted hand wiped the counter. "What do you mean, funny? It was a classic recipe. My grandmother's." "I mean, funny as in, she saw something she shouldn't have. Right before she took a bite." "Saw what? The dust on my ceiling fan?" "No. She saw the mailman, Bob, putting a letter through the Higgins’ door. A letter with a foreign stamp. And now Bob is missing." "Missing? He was just in here for a sourdough loaf. Said he was going to the coast for a week of fishing." "The coast? He told me he was going to the airport. And he didn't buy sourdough. He bought the walnut bread. The one you made with that special honey from the old Hargrove farm." "That's just clover honey. It's my secret to a good crust." "Is it? Because the inspector came by my place last night. He asked if I knew what happens to people who bake with that honey. I didn't. But I do now." "And what's that?" "They don't wake up for breakfast." "That's absurd. I've been using it for years. I had a slice myself this morning." "Did you? And did you sleep well? You look a little pale, dear."
created_at
"2026-09-03T09:50:14.387Z"
9/3/2026, 9:50:14 AM
model
"deepseek/deepseek-v4-flash-20260731"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
425
moderation_latency
(null)
generation_time
42930
tokens_prompt
78
tokens_completion
2560
native_tokens_prompt
65
native_tokens_completion
2721
native_tokens_completion_images
(null)
native_tokens_reasoning
2229
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
0.00137
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788429014-qetaPMi4okVh1BmRBuFT"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788429014-xc2gIfTJq869aMZE5LWH"
upstream_id
"01a066ad15e60090"
provider_responses
0
endpoint_id
"9c83b6fb-0614-4d50-b30b-123a09ba354a"
id
"01a066ad15e60090"
is_byok
false
latency
336
model_permaslug
"deepseek/deepseek-v4-flash-20260731"
provider_name
"Mancer 2"
status
200
total_cost
0.00137
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Mancer 2"
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)