NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1KXZ66EV3HSRMJ3DVPAQRVT
Run Details
Model:
Hy4 Preview (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
1m 54s
Cost:
$0.022928
Provider:
Tencent
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
99.91%
Dialogue to Total Word Ratio
(details)
99.9553%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% words of dialogue between two thieves named Molly and Bill who are planning to break into a children's party to steal all the presents. Only include the prose of the scene without any markdown or commentary.
Model response
Messages
Meta
AI
Molly peered through the hydrangeas. Bill wrestled with a grappling hook and a jump rope. The backyard was a war zone of streamers and a massive mountain of presents. "Remind me why we are doing this?" Bill whispered. "Stealing from a six-year-old?" "Look at that loot, Bill," Molly hissed. "That is not just cheap toys. I see an iPad, a Switch, and fat stacks of gift cards." "Yeah, but the security is brutal," Bill said, rubbing his neck. "Did you see his mom? She has eyes like a hawk and a lethal cupcake dispenser." Molly ignored him, checking her blueprints. The sliding glass door was cracked open, releasing a loud thrum of screeching children and pop music. "We go in through the ball pit," Molly said. "I will distract the birthday boy while you load the sacks." "What is the distraction?" Bill asked. "Are you bringing a fake clown?" "Better," Molly grinned, pulling a pinwheel from her pocket. "I will tell him all the presents are filled with broccoli." "You are evil, Molly. I love it." With a synchronized nod, they tightened their ski masks and crept toward the glowing patio, ready to commit the most adorable felony of their careers.
created_at
"2026-09-03T15:25:02.041Z"
9/3/2026, 3:25:02 PM
model
"tencent/hy4-preview-20260827"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2952
moderation_latency
(null)
generation_time
113558
tokens_prompt
75
tokens_completion
7849
native_tokens_prompt
83
native_tokens_completion
9140
native_tokens_completion_images
(null)
native_tokens_reasoning
8858
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
0.022928362
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788449102-FdluGFdpSx5YCPE5Hb8e"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788449102-XenYltJX9yp3GATbom4P"
upstream_id
"406cee7a-bbd2-4a2b-a716-abae6af72a06"
provider_responses
0
endpoint_id
"ad2a4093-3d2a-41d9-adf1-8b499ac8445d"
id
"406cee7a-bbd2-4a2b-a716-abae6af72a06"
is_byok
false
latency
2952
model_permaslug
"tencent/hy4-preview-20260827"
provider_name
"Tencent"
status
200
total_cost
0.022928362
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%
Matches word count
n/a
neededClean
false
words
201
99.91%
Dialogue to Total Word Ratio
Ratio: 51.72%, Deviation: 1.72%
neededClean
false
wordsTotal
203
wordsDialogue
105
99.9553%