NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1KYBQ0GJR7MZT4QP6CMD78J
Run Details
Model:
Hy4 Preview (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
3m 31s
Cost:
$0.039000
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 behind a plastic flamingo, studying the backyard where a bouncy castle wobbled like a gelatinous monster. Sugar-fueled children sprinted past, shrieking with the wild energy only cake and juice boxes could create. Bill adjusted his fake moustache, which kept sliding toward his left eyebrow. Their plan was simple, which worried Molly more than any laser grid. They would pose as party entertainers, sneak inside during the magic show, and vanish with every unwrapped present before the piƱata broke. "Ready to ruin birthdays?" Bill asked. "Only the good ones," Molly said. "We'll sneak in as clowns," Bill said. "Clowns are terrifying," Molly said. "Exactly. Fear opens doors," Bill said. He handed her a wig that smelled of burnt rubber. Molly eyed the gift table, piled high with boxes and one heavy drum set. Somewhere a toddler wailed, sounding like a tiny siren. Molly checked her watch. The magic show started in three minutes, giving them just enough time to trip over a garden gnome, upset a tray of cupcakes, and question every life choice that led them here. Bill saluted, tripped on the flamingo, and fell into a hydrangea bush. Molly sighed. Professional criminals, she decided, deserved better backup.
created_at
"2026-09-03T15:31:52.47Z"
9/3/2026, 3:31:52 PM
model
"tencent/hy4-preview-20260827"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1699
moderation_latency
(null)
generation_time
210992
tokens_prompt
75
tokens_completion
13672
native_tokens_prompt
83
native_tokens_completion
15566
native_tokens_completion_images
(null)
native_tokens_reasoning
15277
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
0.038999788
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788449512-6DPrcf8EJhRSMjvgMJuq"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788449512-hEUkr5VwVTebeJUBzUss"
upstream_id
"8e27968e-1e15-43a2-833b-896b10957005"
provider_responses
0
endpoint_id
"ad2a4093-3d2a-41d9-adf1-8b499ac8445d"
id
"8e27968e-1e15-43a2-833b-896b10957005"
is_byok
false
latency
1698
model_permaslug
"tencent/hy4-preview-20260827"
provider_name
"Tencent"
status
200
total_cost
0.038999788
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: 9.95%, Deviation: 0.05%
neededClean
false
wordsTotal
201
wordsDialogue
20
100.0000%