NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1M1QNJBQKPW4QF61BP56SXB
Run Details
Model:
Hy4 Preview (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
1m 40s
Cost:
$0.016658
Provider:
Tencent
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 gave a cheerful jingle. Warm air, thick with yeast and browned butter, wrapped around the quiet morning. Sunlight striped the worn wooden floor, and a case of glazed pastries glistened near the register. “You’re here early. The cinnamon rolls aren’t even out of the oven.” “I’m not here for cinnamon rolls. I’m here about the judging table.” “The what?” “Someone switched your award-winning blueberry pie with a supermarket one. The head judge noticed before the ribbon was pinned.” “That’s ridiculous. My pie sat right there, beneath the lace cloth, exactly where I left it.” “It was there. Then it wasn’t. And now the mayor’s assistant is telling everyone your filling was too runny.” “Too runny? My filling is never runny. Who would do such a thing?” “That’s exactly what we’re going to find out. Start by telling me who had access to the kitchen before the fair.” “Only Martha, my neighbor of thirty years. She borrowed my rolling pin and returned it polished.” “Neighbor or not, somebody wanted that blue ribbon. And I intend to sift the truth out of this town, one crumb at a time.” A pan clattered somewhere in the back, and the scent of scorched sugar drifted through the warm room.
created_at
"2026-09-03T16:30:49.938Z"
9/3/2026, 4:30:49 PM
model
"tencent/hy4-preview-20260827"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1586
moderation_latency
(null)
generation_time
100046
tokens_prompt
78
tokens_completion
6499
native_tokens_prompt
83
native_tokens_completion
6633
native_tokens_completion_images
(null)
native_tokens_reasoning
6339
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
0.016658355
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788453049-RU05gmjzwrURIbmWMd6u"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788453049-C2EVmK2hB1I6De3cS1oq"
upstream_id
"a4513cdc-0660-487e-9db6-849685af5c30"
provider_responses
0
endpoint_id
"ad2a4093-3d2a-41d9-adf1-8b499ac8445d"
id
"a4513cdc-0660-487e-9db6-849685af5c30"
is_byok
false
latency
1586
model_permaslug
"tencent/hy4-preview-20260827"
provider_name
"Tencent"
status
200
total_cost
0.016658355
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Tencent"
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)