NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1M1NNZZ0MQMDE40WJX6CMJN
Run Details
Model:
Hy4 Preview (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
3m 6s
Cost:
$0.034761
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
The getaway van crouched behind a hedge shaped like a duck. A very plastic flamingo judged them from the lawn. Bill checked his reflection in a spoon, adjusted his paper hat, and frowned at the suburban house glowing with balloons. Somewhere inside, children chanted for more sugar. Molly unfolded a crumpled invitation. “Phase one,” she whispered, “is infiltration. You’re Uncle Bob the magician. I’m your silent, beautiful assistant. We mingle, locate the present table, and vanish with the swag.” Bill groaned and adjusted his fake mustache. It immediately fell into his lap. Bill paled. “Last time I did magic, I sawed a cake in half and the birthday girl screamed for an hour. I’m banned from three party supply stores.” Molly ignored him and handed him a plastic wand. “That was parlor magic for adults. This is a kid. Their expectations are lower. Also, their security is a golden retriever named Mr. Wiggles.” Bill stared at the cheerful chaos. Children hurled cake. A piñata leaked candy. Somewhere, a balloon animal died. “Fine,” he said. “But if a toddler bites me, I’m keeping the loot.” Molly nodded. “Deal. Put on the nose. And remember, no actual magic. Just grab and grin.”
created_at
"2026-09-03T16:29:44.837Z"
9/3/2026, 4:29:44 PM
model
"tencent/hy4-preview-20260827"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2302
moderation_latency
(null)
generation_time
185524
tokens_prompt
75
tokens_completion
12101
native_tokens_prompt
83
native_tokens_completion
13871
native_tokens_completion_images
(null)
native_tokens_reasoning
13577
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
0.034760593
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788452984-SHr0w31hvb58oJULSEIi"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788452984-ZGCgYMfmZU0n3nWWX0f5"
upstream_id
"b3007f10-76de-47da-8e02-abdfce1e816b"
provider_responses
0
endpoint_id
"ad2a4093-3d2a-41d9-adf1-8b499ac8445d"
id
"b3007f10-76de-47da-8e02-abdfce1e816b"
is_byok
false
latency
2199
model_permaslug
"tencent/hy4-preview-20260827"
provider_name
"Tencent"
status
200
total_cost
0.034760593
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%