NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2FB6T2ERMRPYR2BESDA52G
Run Details
Model:
DeepSeek V4 Flash
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
5.5s
Cost:
$0.000099
Provider:
DeepSeek
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
“Blueberry’s gone again. I can’t find a single one in the whole basket.” “That’s because you left the back door open. Blueberry pie doesn’t wander off by itself.” “Oh, very funny. You know what I mean. The jar—the one from Mrs. Higgins’s pantry—it’s not where I left it.” “Behind the flour? I put my rolling pin there this morning.” “No, not behind it. Inside. The little jar with the faded label. It’s empty now, and I found this on the floor.” A soft clink as something metal was set on the counter. “A key. Small, brass. Fit for a lockbox, maybe.” A pause, filled only with the hum of the old display case. “Well, that’s a first. Usually it’s a crumb trail or a dropped handkerchief. You sure it’s not one of yours?” “Positive. I only have two keys—the shop’s and my apartment’s. This one’s got a little scratch on it, like a cat’s claw. And Mrs. Higgins swore that jar was just her mother’s old jam. Empty for years, she said.” “People lie, dear. Especially about jam jars with hidden keys.” “So what do we do with it?” A wooden spoon tapped twice against a mixing bowl. “We bake. And we wait. Someone’s bound to come looking for it—or for the jam that isn’t jam.”
created_at
"2026-04-25T14:05:23.655Z"
4/25/2026, 2:05:23 PM
model
"deepseek/deepseek-v4-flash-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
725
moderation_latency
(null)
generation_time
5286
tokens_prompt
81
tokens_completion
340
native_tokens_prompt
65
native_tokens_completion
320
native_tokens_completion_images
(null)
native_tokens_reasoning
0
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"
usage
0.0000987
router
(null)
provider_responses
0
endpoint_id
"722e0746-2034-4d6e-a08f-e6271849ee9e"
id
"a63a8d8a-ef26-43b8-90ac-b86f71c4155e"
is_byok
false
latency
430
model_permaslug
"deepseek/deepseek-v4-flash-20260423"
provider_name
"DeepSeek"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777125923-L3XfwLYMM19djM5QLqqD"
session_id
(null)
api_type
"completions"
id
"gen-1777125923-rPlTaXC4kH8bWlnnBC85"
upstream_id
"a63a8d8a-ef26-43b8-90ac-b86f71c4155e"
total_cost
0.0000987
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepSeek"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)