NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1M1VV2ZW67KJ5B3W0693G77
Run Details
Model:
Hy4 Preview (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
3m 4s
Cost:
$0.033955
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
Molly adjusted her goggles and glared at the suburban fortress. Balloons bobbed like sugary sentries in the moonlight. Bill knelt beside her, stuffing a sack labeled LOOT into his fanny pack. Their target was a children's birthday party for a tiny tyrant named Princess Sparkles. The plan was simple, illegal, and aimed at stealing all the presents before the cake. The guest list included one screaming violinist, three sugar crazed cousins, and a dog wearing a party hat. Molly had disguised the getaway van as an ice cream truck, though the siren still loudly played polka music. Bill mapped every route except the one through the bounce house, which he called a trap. "The piñata is watching us," Molly whispered. Bill squinted at a lopsided donkey piñata. "Then I'll distract the cake," Bill said. Molly snatched his map, drawn in crayon. "Nobody steals presents before cake," Molly said. Bill patted a glittery mustache onto his lip. "I brought a fake mustache," Bill said. Molly groaned. They would enter as clowns, exit as legends, and hopefully avoid the toddler with a juice box sword. Timing was everything. The piñata swung creakingly in the breeze. Somewhere, a bubble machine plotted their doom.
created_at
"2026-09-03T16:33:06.679Z"
9/3/2026, 4:33:06 PM
model
"tencent/hy4-preview-20260827"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1572
moderation_latency
(null)
generation_time
183600
tokens_prompt
75
tokens_completion
12335
native_tokens_prompt
83
native_tokens_completion
13549
native_tokens_completion_images
(null)
native_tokens_reasoning
13264
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
0.033955271
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788453186-7cfBNrbqBdPyNaLlBZcS"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788453186-BlY9BFJtPK3l9aFYEvYQ"
upstream_id
"8499e520-d462-4c3a-9d76-68d1717fc2f0"
provider_responses
0
endpoint_id
"ad2a4093-3d2a-41d9-adf1-8b499ac8445d"
id
"8499e520-d462-4c3a-9d76-68d1717fc2f0"
is_byok
false
latency
1572
model_permaslug
"tencent/hy4-preview-20260827"
provider_name
"Tencent"
status
200
total_cost
0.033955271
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%