NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1M1M5G0XMA9K87A4NN163XZ
Run Details
Model:
Hy4 Preview (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
3m 9s
Cost:
$0.037172
Provider:
Tencent
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
96.68%
Dialogue to Total Word Ratio
(details)
98.3413%
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 studied the suburban fortress through binoculars, its vinyl siding glowing with the smug cheer of a house that had never known regret. Balloons bobbed by the mailbox like party favors. Bill crouched in the hydrangeas, wearing a turtleneck despite July heat, because stealth required fashion sacrifices. "Ready to ruin a six-year-old's birthday?" he whispered. Molly lowered the binoculars. "Only if we leave the piƱata. I have standards." Bill nodded solemnly. "Fine. No tears, no tantrums." They crawled toward the back gate, past a sign reading "Welcome to Princess Destiny's Castle of Joy," which made Molly reconsider every choice that led her here. A drawbridge blocked the path, guarded by a motion-activated dragon that shrieked when disturbed. Bill disabled it with a paperclip and gum, because professional thieves always carried office supplies. Inside the fence, the backyard looked like a toy store had exploded inside a rainbow. A table groaned under all the presents wrapped in pink paper. Molly's eyes gleamed. This was the score of a lifetime, assuming they could avoid the parents, the clown, and a golden retriever named Chaos. She signaled for Bill to follow, stepping over a discarded juice box and the crushed dreams of childhood.
created_at
"2026-09-03T16:28:55.176Z"
9/3/2026, 4:28:55 PM
model
"tencent/hy4-preview-20260827"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1476
moderation_latency
(null)
generation_time
188702
tokens_prompt
75
tokens_completion
13534
native_tokens_prompt
83
native_tokens_completion
14835
native_tokens_completion_images
(null)
native_tokens_reasoning
14558
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
0.037171557
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788452935-6vGyhuDvoRaIMa2kbMMQ"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788452935-Hk5Yv5ukKYPiRsNVtzD0"
upstream_id
"3ea325bf-5c02-43ed-b147-3a3448d2002c"
provider_responses
0
endpoint_id
"ad2a4093-3d2a-41d9-adf1-8b499ac8445d"
id
"3ea325bf-5c02-43ed-b147-3a3448d2002c"
is_byok
false
latency
1475
model_permaslug
"tencent/hy4-preview-20260827"
provider_name
"Tencent"
status
200
total_cost
0.037171557
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
96.68%
Dialogue to Total Word Ratio
Ratio: 14.29%, Deviation: 4.29%
neededClean
false
wordsTotal
203
wordsDialogue
29
98.3413%