NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1KZ7WPFXT57JXX083EFE8DK
Run Details
Model:
Hy4 Preview (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
3m 13s
Cost:
$0.035201
Provider:
Tencent
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
100.0000%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 crouched low, binoculars fogging as she studied the target. The backyard was a pastel war zone. Balloons bobbed like colorful land mines. A plastic castle squatted on the lawn, and beneath a banner reading Happy Birthday, Timmy, piles of presents glittered with greedy menace. Bill crouched beside her, his black catsuit straining around a belly built from years of heist snacks. He clutched a grappling hook, a crowbar, and a bag labeled Totally Legit Charity. Molly lowered them. "In at eight. Clown break. Four minutes." Bill frowned. "Four minutes for every gift?" "Exactly. Every last one," Molly said. They bumped fists and crept toward the side gate. A sleepy corgi in a pirate costume lifted one ear, judged them unworthy, and returned to sleep. Molly picked the lock with a hairpin and a confident smile. The gate squealed like a toddler denied cake. She winced. Bill shoved a cookie into the hinge. The gate purred open. Inside, the party raged. Children screamed with joy while parents screamed with regret. Somewhere a piƱata swung far too close to a ceiling fan. Molly scanned the gift table and Bill rubbed his hands together. "Then blame the pony," Bill grinned. They moved.
created_at
"2026-09-03T15:47:15.801Z"
9/3/2026, 3:47:15 PM
model
"tencent/hy4-preview-20260827"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1799
moderation_latency
(null)
generation_time
193077
tokens_prompt
75
tokens_completion
12336
native_tokens_prompt
83
native_tokens_completion
14047
native_tokens_completion_images
(null)
native_tokens_reasoning
13749
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
0.035200769
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788450435-goHVp6HRYW0vDkMoz5fu"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788450435-xf6sGW45YruRz0bmlVMn"
upstream_id
"bf363920-eca2-417c-bcaa-ae569eb019c4"
provider_responses
0
endpoint_id
"ad2a4093-3d2a-41d9-adf1-8b499ac8445d"
id
"bf363920-eca2-417c-bcaa-ae569eb019c4"
is_byok
false
latency
1799
model_permaslug
"tencent/hy4-preview-20260827"
provider_name
"Tencent"
status
200
total_cost
0.035200769
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
200
100.00%
Dialogue to Total Word Ratio
Ratio: 10.00%, Deviation: 0.00%
neededClean
false
wordsTotal
200
wordsDialogue
20
100.0000%