NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2FEBXPN3X3H77KDDSD47NQ
Run Details
Model:
DeepSeek V4 Pro
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
15.7s
Cost:
$0.000258
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
The bell above the door chimed, ushering in the scent of rain-soaked pavement and lilac perfume. “You’ve been staring at that éclair for ten minutes. It’s not a crystal ball.” “Maybe not. But the way Phyllis snatched the last lemon tart before Edna could even point got me thinking. It was very… targeted.” “Targeted? It’s a bake sale, not a military operation. Doris, she claimed her hip was acting up. She shuffled.” “Did she, though? That woman practically sprinted past the sourdough. And consider the timing. The very morning Edna announces she’s challenging Phyllis for treasurer of the garden club? A lemon tart, Edna’s absolute favorite, the last one, gone. It’s a message.” “You think Phyllis faked a limp for pastry-based psychological warfare?” “I’m saying the custard in that tart was suspiciously perfect. Almost distractingly so. And now Edna’s home with a ‘headache’ and Phyllis is buying celebratory scones. Two cranberry-orange. She only ever buys one.” “Dear lord. You’re right. She’s not just hoarding carbs, she’s weaponizing them.”
created_at
"2026-04-25T14:07:14.049Z"
4/25/2026, 2:07:14 PM
model
"deepseek/deepseek-v4-pro-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1076
moderation_latency
(null)
generation_time
8586
tokens_prompt
81
tokens_completion
297
native_tokens_prompt
65
native_tokens_completion
264
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
0.000257955
router
(null)
provider_responses
0
endpoint_id
"d084170b-dd99-4e53-9ae1-b63881f3cfbf"
id
"d3764ee9-79a9-4863-9106-2460b23f09d4"
is_byok
false
latency
461
model_permaslug
"deepseek/deepseek-v4-pro-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-1777126034-zRSS8JjkJ40vTzREfajd"
session_id
(null)
api_type
"completions"
id
"gen-1777126034-1Dt2EI253NPM75d2v0S6"
upstream_id
"d3764ee9-79a9-4863-9106-2460b23f09d4"
total_cost
0.000257955
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)