NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1M25MRY6M37XA5ZFQFJRQW0
Run Details
Model:
Hy4 Preview (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
3m 40s
Cost:
$0.037707
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 90% 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
Behind an inflatable castle, Molly and Bill crouched. Molly said, "Bill, the birthday boy is turning five, and the loot is stacked higher than a nursery block tower." Bill said, "I'll wear the clown nose. Nothing says innocent like a honk." "We are not stealing from babies," Molly said. "We're reallocating wrapping paper." "Right. And the presents? We'll tell the kids the gifts went to a toy retirement home." "You'll distract the parents with a magic trick. Pull a rabbit from your pants." "My pants barely hold my wallet, let alone a rabbit." "Then pull a juice box. Kids respect hydration." "What if the birthday girl screams?" "Screams are just applause with higher pitch. Now grab the getaway wagon—the one with the training wheels." "That's a tricycle, Molls." "Perfect. Nobody suspects a tricycle fleeing the scene of a juice-box heist." Bill said, "I still say we should've brought a bigger sack. My pockets are already completely full of sticky pink party glitter." Molly said, "Glitter is the fairy dust of felons. Besides, the loot goes in the piñata we stole last week." Bill said, "Remind me why we didn't just steal the piñata candies and call it a day?"
created_at
"2026-09-03T16:38:27.88Z"
9/3/2026, 4:38:27 PM
model
"tencent/hy4-preview-20260827"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1987
moderation_latency
(null)
generation_time
219469
tokens_prompt
75
tokens_completion
12831
native_tokens_prompt
83
native_tokens_completion
15049
native_tokens_completion_images
(null)
native_tokens_reasoning
14760
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
0.037706771
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788453507-mEcV4cN8UWgJWw52BQ37"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788453507-AASplpH0w8BXEtNAKkzS"
upstream_id
"c7ea0099-259c-4c78-bec7-6b6ddaf071ae"
provider_responses
0
endpoint_id
"ad2a4093-3d2a-41d9-adf1-8b499ac8445d"
id
"c7ea0099-259c-4c78-bec7-6b6ddaf071ae"
is_byok
false
latency
1987
model_permaslug
"tencent/hy4-preview-20260827"
provider_name
"Tencent"
status
200
total_cost
0.037706771
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: 90.05%, Deviation: 0.05%
neededClean
false
wordsTotal
201
wordsDialogue
181
100.0000%