NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1KZCMN7XQYZNGK81TQ756MH
Run Details
Model:
Hy4 Preview (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
4m 28s
Cost:
$0.050474
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 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
Molly and Bill crouched behind a balloon arch, plotting to break into the children's party and steal all the presents. A bouncy castle shuddered nearby. A folding table sagged beneath enough presents to fund a yacht. Somewhere, a toddler screamed with the authority of a tax auditor. Molly adjusted her glittery wings and squinted through binoculars. “Here’s the plan,” she said. “I’ll distract the parents with cupcakes while you load the loot.” Bill tugged his oversized clown shoes. “Cupcakes again?” he groaned. “Last time, frosting ended up in my ear.” “That was strategic,” Molly replied. “Now focus. Grab the big boxes, skip the socks.” Bill frowned. “There’s a tractor, a dinosaur, and a potato karaoke machine.” “Perfect,” she said. “The potato funds our retirement. Meet me by the piñata.” “And if a kid attacks?” “Tell them you’re a naptime consultant,” Molly said. “Then run.” Bill nodded, eyeing the magician. “What about the magician?” “He only knows one trick,” she whispered. “I’ve bribed him with juice.” “Smooth.” Molly checked her watch. “Remember the signal?” Bill grinned. “The one where you scream 'free cake'?” “Exactly,” Molly said. “Chaos is a ladder.” Bill sighed and picked up an empty burlap sack labeled Swag.
created_at
"2026-09-03T15:49:51.408Z"
9/3/2026, 3:49:51 PM
model
"tencent/hy4-preview-20260827"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1258
moderation_latency
(null)
generation_time
267943
tokens_prompt
75
tokens_completion
16786
native_tokens_prompt
83
native_tokens_completion
20154
native_tokens_completion_images
(null)
native_tokens_reasoning
19825
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
0.050474376
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788450591-zTnBXuhBaVbsBOLoUtqP"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788450591-MwlHDj149s5RgPrfqlhM"
upstream_id
"d209517b-53da-466e-8d14-7c93115cc9de"
provider_responses
0
endpoint_id
"ad2a4093-3d2a-41d9-adf1-8b499ac8445d"
id
"d209517b-53da-466e-8d14-7c93115cc9de"
is_byok
false
latency
1258
model_permaslug
"tencent/hy4-preview-20260827"
provider_name
"Tencent"
status
200
total_cost
0.050474376
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: 50.00%, Deviation: 0.00%
neededClean
false
wordsTotal
200
wordsDialogue
100
100.0000%