NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1M1Z0QBF6TC482C5ZQFD3F7
Run Details
Model:
Hy4 Preview (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
3m 8s
Cost:
$0.035478
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
The backyard looked like a war zone. A bouncy castle wobbled beside a table buried under wrapped presents. Molly crouched behind a prickly hedge, her sweater snagged on a garden gnome. Bill wrestled with a giant blueprint. “Do you have the sack?” Molly asked. Bill patted his pockets and grinned. “Yes, and a crowbar shaped like a unicorn,” he said. Molly checked her watch, eying the cake chaos. “Perfect. We sneak in during cake chaos,” she whispered. Bill adjusted his mask and imagined the loot. A child shrieked, providing cover. Molly signaled, and they crept toward the gift table like cats. The crowd sang a birthday song. A clumsy clown tripped over a balloon animal. Molly froze, one gloved hand raised. Bill pretended to be a potted plant, which fooled nobody but bought three seconds. A toddler waddled past, staring at Bill’s unicorn crowbar with suspicious eyes. Molly held her breath and gently redirected the child toward the cupcake tower. Bill mouthed a thank you. They reached the gift table, where a glittery mound of presents waited like treasure in a diaper commercial. Molly pulled a sack from her pocket, ready to commit the most precious crime of the century.
created_at
"2026-09-03T16:34:50.737Z"
9/3/2026, 4:34:50 PM
model
"tencent/hy4-preview-20260827"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1437
moderation_latency
(null)
generation_time
187312
tokens_prompt
75
tokens_completion
12164
native_tokens_prompt
83
native_tokens_completion
14158
native_tokens_completion_images
(null)
native_tokens_reasoning
13874
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
0.03547838
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788453290-0ttlFNqPGe2SO89ZVUeo"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788453290-TBIXtxgjmnVDhkYxkenr"
upstream_id
"f6a830db-4dde-4ca8-8ba6-56bb827f5244"
provider_responses
0
endpoint_id
"ad2a4093-3d2a-41d9-adf1-8b499ac8445d"
id
"f6a830db-4dde-4ca8-8ba6-56bb827f5244"
is_byok
false
latency
1436
model_permaslug
"tencent/hy4-preview-20260827"
provider_name
"Tencent"
status
200
total_cost
0.03547838
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%