NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-11-11-01M75R059BG5Y5AD5BTYWMMTYG
Run Details
Model:
Hy4 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
35.6s
Cost:
$0.005083
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 scent of browned butter and cardamom hung heavy beneath the tin ceiling. Outside, Main Street was still waking up. "Tell me again exactly where you found it." "Inside the hollow of the braided brioche. The one set aside for the rector." "And you’re certain it wasn’t there when you shaped the dough at four?" "Positive. I dusted that loaf myself. Not a single blue ribbon poking out, let alone one stained with... whatever this is." A butter knife nudged a scrap of satin across the speckled marble. "It’s blackberry. Not yours. You only use strawberries this early in the season." "Old Man Miller’s patch is the only one fruiting. Over by the gristmill." "But he swore off ribbons when his wife took the judging panel in '98." "Someone else was in that patch, then. Or wanted us to think so." "The back latch was unbolted when I came in, too. No broken glass, no flour footprints. Just a smudge of purple on the brass." "The kettle’s on. We won’t solve a thing before Earl Grey, but we’d best figure it out before the mayor wants his cruller. He expects that ribbon in the display case by eight." "Then we start with who knew the rector wasn't coming."
created_at
"2026-11-11T16:45:31.323Z"
11/11/2026, 4:45:31 PM
model
"tencent/hy4-20261104"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1197
moderation_latency
(null)
generation_time
35567
tokens_prompt
78
tokens_completion
3611
native_tokens_prompt
83
native_tokens_completion
4037
native_tokens_completion_images
(null)
native_tokens_reasoning
3748
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
0.005082879
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.22.2; linux; x64))"
http_referer
(null)
request_id
"req-1794415531-HqbalwCz8VbJmQTS4sKU"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1794415531-PpZpFtqQkWPHJBImYSGq"
upstream_id
"f697ccb1-6647-4e77-b492-b86d282b359d"
provider_responses
0
endpoint_id
"b5b076de-19fd-4e5c-adc2-2420a425969e"
id
"f697ccb1-6647-4e77-b492-b86d282b359d"
is_byok
false
latency
1197
model_permaslug
"tencent/hy4-20261104"
provider_name
"Tencent"
status
200
total_cost
0.005082879
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)