NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1KYM1FWJRDMK27D6HBKJY8M
Run Details
Model:
Hy4 Preview (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
3m 17s
Cost:
$0.037589
Provider:
Tencent
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.9985%
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
The stolen blueprint of the party palace fluttered in Molly’s grip. Bill crouched behind a plastic unicorn, studying the security system: one overworked mom, a toddler with a juice box, and a very aggressive balloon animal. He wiped frosting from his binoculars. Somewhere inside, a sugar-crazed four-year-old screamed for cake. Chaos reigned. “Remind me again why we’re doing this?” Bill whispered. “Last time, you cried at naptime.” Molly rolled her eyes and pulled a glittery clown wig from her backpack. She shook it, releasing a small cloud of confetti and one traumatized moth. “Because this party has a pony, a magician, and presents guarded only by sticky fingers. We’ll walk in as entertainers.” Bill eyed the wig. “You expect me to squeeze into a pony costume? My knees already filed a complaint.” “You’ll be the back half,” Molly said. “Just sway gently and don’t eat the hay.” “And the loot?” Molly pointed at a rainbow piñata hanging from the ceiling. “We fill it with presents, then accidentally smash it open outside. Tragic but believable.” Bill sighed. “Fine. But if a toddler proposes to me again, I’m keeping the ring pop.” Molly grinned. “Deal. Try not to neigh at the police.”
created_at
"2026-09-03T15:36:25.347Z"
9/3/2026, 3:36:25 PM
model
"tencent/hy4-preview-20260827"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1285
moderation_latency
(null)
generation_time
197253
tokens_prompt
75
tokens_completion
12294
native_tokens_prompt
83
native_tokens_completion
15002
native_tokens_completion_images
(null)
native_tokens_reasoning
14696
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
0.037589224
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788449785-uv4LoLs8PhXSlPUeUTJX"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788449785-yfbpB3bakIBnvgkm7T6N"
upstream_id
"35b9d69e-c95d-48a9-8608-1dab59d94baa"
provider_responses
0
endpoint_id
"ad2a4093-3d2a-41d9-adf1-8b499ac8445d"
id
"35b9d69e-c95d-48a9-8608-1dab59d94baa"
is_byok
false
latency
1284
model_permaslug
"tencent/hy4-preview-20260827"
provider_name
"Tencent"
status
200
total_cost
0.037589224
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: 49.26%, Deviation: 0.74%
neededClean
false
wordsTotal
203
wordsDialogue
100
99.9985%