NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1KAHES9VGY9TEMSG356K6K1
Run Details
Model:
DeepSeek V4 Pro 0813 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
13.3s
Cost:
$0.002070
Provider:
DigitalOcean
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 fresh bread, the air warm and sugar-dusted. Behind the counter, a tray of untouched lemon squares sat beside a cooling rack. “You’re not really selling those, are you? Not after what happened.” “They’re just pastries. Nothing wrong with a little lemon and butter.” “Millie was in here yesterday. Bought half a dozen of the same ones. Now she’s in the hospital.” “That’s a terrible thing to say out loud.” “I’m not saying it. I’m asking why the health inspector hasn’t been by yet.” “Because there’s nothing to inspect. Flour, sugar, eggs, lemon zest. That’s all that’s in them.” “And nutmeg. Don’t forget the nutmeg.” A pause. The cash register drawer slid open and then shut with a soft click. The bell above the door jingled, but no one new came in—just the wind pushing against the glass. “Millie’s allergic. Everyone in town knows that.” “She said she wanted one bite. It was her birthday.” “Her birthday was in March. It’s October.” “Then maybe she forgot her own birthday.” The second voice dropped lower, just above the hum of the refrigerator case. “You and I both know she didn’t forget anything.”
created_at
"2026-09-03T09:45:29.14Z"
9/3/2026, 9:45:29 AM
model
"deepseek/deepseek-v4-pro-20260813"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1594
moderation_latency
(null)
generation_time
13213
tokens_prompt
78
tokens_completion
598
native_tokens_prompt
65
native_tokens_completion
501
native_tokens_completion_images
(null)
native_tokens_reasoning
216
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
0.00206976
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788428729-fJPw0m3IQjgxWerngHpv"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788428729-VOsyEkdrohKYHwjDFOFm"
upstream_id
"chatcmpl-cc6ef54a-9031-4f4c-beb2-507f67a49e60"
provider_responses
0
endpoint_id
"928ab2e9-a85f-427f-adcb-15b2394c70d5"
id
"chatcmpl-cc6ef54a-9031-4f4c-beb2-507f67a49e60"
is_byok
false
latency
1561
model_permaslug
"deepseek/deepseek-v4-pro-20260813"
provider_name
"DigitalOcean"
status
200
total_cost
0.00206976
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DigitalOcean"
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)