NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1K9MWBV2ZZPVDZ4213EFDTH
Run Details
Model:
DeepSeek V4 Flash 0731 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
29.5s
Cost:
$0.000126
Provider:
DeepInfra
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 chimed, and the scent of cinnamon wrapped around the visitor like a familiar hug. Behind the counter, a flour-dusted apron wiped its hands on a towel. "Morning, Nora. The usual?" "Please. And a sticky bun, if they're fresh." "They're always fresh. You know that." A paper bag crinkled, then the soft thump of a pastry landing inside. "But I saw something odd when I came in at four." "Oh?" The word hung in the air, sharper than intended. "Lights on in the back office. Old Man Higgins's office. He's been dead three months." A pause. The cash register drawer slid open with a metallic ring. "Maybe his daughter forgot to turn them off." "Maybe. But the blinds were shut, and there was a shadow moving. Slow, like it was searching." The bag rustled again. "You're telling me this because?" "Because you're the one who found him. And because the shadow was wearing your red coat." The bell chimed again, but no one entered. The sticky bun sat on the counter, untouched.
created_at
"2026-09-03T09:29:52.777Z"
9/3/2026, 9:29:52 AM
model
"deepseek/deepseek-v4-flash-20260731"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
269
moderation_latency
(null)
generation_time
29443
tokens_prompt
78
tokens_completion
706
native_tokens_prompt
144
native_tokens_completion
637
native_tokens_completion_images
(null)
native_tokens_reasoning
398
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
0.00012618
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788427792-iVh0YIRvbRpJLAITV9cp"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788427792-he9C5VE2OGVhNbAvIvRt"
upstream_id
"chatcmpl-RQWC1h8kVt73SAESj2nqA1uP"
provider_responses
0
endpoint_id
"c1980fff-0a72-4bce-8d62-a7d3fc582200"
id
"chatcmpl-RQWC1h8kVt73SAESj2nqA1uP"
is_byok
false
latency
61
model_permaslug
"deepseek/deepseek-v4-flash-20260731"
provider_name
"DeepInfra"
status
200
total_cost
0.00012618
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
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)