NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1KZVWHG2CBQ4HM2Z46B559R
Run Details
Model:
Hy4 Preview (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
3m 32s
Cost:
$0.039885
Provider:
Tencent
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.9997%
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 crowded backyard smelled like frosting, sugar, and chaos. Molly crouched behind a plastic slide and unfolded a napkin map drawn in crayon. "Okay, Bill. We slip in during the piƱata blindfold, grab all the presents, and vanish." Bill adjusted his oversized clown shoes and frowned. "Molly, I'm six-foot-four. In these shoes, I'm a parade float." Molly tapped the map with a glittery pen. "You're the distraction. Trip over the ball pit and yell 'free candy.'" Bill raised one skeptical eyebrow. "That's entrapment of minors. Also, I'm lactose intolerant, remember?" Molly rolled her eyes so hard it hurt. "Fine, yell 'puppies.' I'll wear the cape and hide the loot in my hat." Bill folded his arms and deflated slightly. "A hat can't hold a bicycle, Molls." Molly grinned and wiggled her fingers. "It can if the bicycle is a tricycle and the hat is a duffel bag." Bill nodded, then panicked. "What's the getaway?" Molly pointed at a small toy car near the fence. "That motorized wagon. Top speed: brisk walk." Bill stared at it, betrayed. "If we survive, I'm keeping the juice boxes." Molly slung an empty duffel bag over her shoulder and stood, ready to commit felony cute.
created_at
"2026-09-03T15:58:10.998Z"
9/3/2026, 3:58:10 PM
model
"tencent/hy4-preview-20260827"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1307
moderation_latency
(null)
generation_time
212031
tokens_prompt
75
tokens_completion
12786
native_tokens_prompt
83
native_tokens_completion
15920
native_tokens_completion_images
(null)
native_tokens_reasoning
15611
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
0.039885142
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788451091-kXlEecdPOofS2UHLIhSS"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788451091-4ob4GIgVINOBS1Ew318R"
upstream_id
"6bab8cc9-c938-47f5-97be-5df558b62a1d"
provider_responses
0
endpoint_id
"ad2a4093-3d2a-41d9-adf1-8b499ac8445d"
id
"6bab8cc9-c938-47f5-97be-5df558b62a1d"
is_byok
false
latency
1307
model_permaslug
"tencent/hy4-preview-20260827"
provider_name
"Tencent"
status
200
total_cost
0.039885142
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: 50.50%, Deviation: 0.50%
neededClean
false
wordsTotal
202
wordsDialogue
102
99.9997%