NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1M0NS1C6FDKYQ46G1YY57WZ
Run Details
Model:
Hy4 Preview (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
2m 9s
Cost:
$0.027508
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 adjusted her oversized, brightly polka-dotted clown nose and scowled through the binoculars. The suburban backyard looked like a war zone, complete with a brightly colored bounce house and a screaming horde of sugar-fueled kindergarteners. This was supposed to be a simple smash-and-grab, but the sheer, overwhelming volume of constant noise made her teeth ache. Beside her, Bill was wrestling a massive, deflated inflatable T-Rex costume into a duffel bag. “Do we really have to take everything?” Bill whispered, checking his watch. “Even the half-eaten cake?” “Every last wrapped box, Bill. Don't be so soft,” Molly replied. She traced the blueprint with a single gloved finger. Their primary entry point was the pantry window, right past the magician. The real challenge wasn't the parents; it was actually navigating the sticky, juice-box-covered linoleum without slipping. They definitely needed a distraction. Molly planned to release a dozen hyperactive ferrets into the bouncy castle, causing chaos while they slipped quietly upstairs to the gift table. It was foolproof, mostly. Bill nodded, pulling out a water pistol filled with sedatives, just in case a toddler got too rowdy. They zipped up their absurd disguises, ready to commit the most humiliating crime of their careers.
created_at
"2026-09-03T16:12:19.378Z"
9/3/2026, 4:12:19 PM
model
"tencent/hy4-preview-20260827"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1567
moderation_latency
(null)
generation_time
128557
tokens_prompt
75
tokens_completion
8600
native_tokens_prompt
83
native_tokens_completion
10971
native_tokens_completion_images
(null)
native_tokens_reasoning
10686
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
0.027507693
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788451939-8uTMc0GtkFakdr4OzcwJ"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788451939-yyBZs1nFojlaaySh02zp"
upstream_id
"4c68491d-81a3-4b89-9d87-7dac7c9b9b7b"
provider_responses
0
endpoint_id
"ad2a4093-3d2a-41d9-adf1-8b499ac8445d"
id
"4c68491d-81a3-4b89-9d87-7dac7c9b9b7b"
is_byok
false
latency
1567
model_permaslug
"tencent/hy4-preview-20260827"
provider_name
"Tencent"
status
200
total_cost
0.027507693
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: 10.14%, Deviation: 0.14%
neededClean
false
wordsTotal
207
wordsDialogue
21
100.0000%