NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1M0XPJEHR19MHVA932DPKJK
Run Details
Model:
Hy4 Preview (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
3m 59s
Cost:
$0.043894
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
Molly checked the window. “Okay, Bill, the coast is finally clear. The silly birthday clown is crying right now in the bouncy castle again.” “Why is the silly birthday clown crying now?” Bill asked. “Did someone pop his last balloon animal on purpose?” “No,” Molly said. “He realized the stuffed piñata is actually his union rep. Now listen closely, because this part is important. We sneak in through the gift table, grab every single shiny present, and leave before the kids open the really good loot.” “Every single last present?” Bill whispered. “Even the silly ones wrapped in that shiny dinosaur paper?” “Especially those right there,” Molly said. “Kids absolutely love dinosaurs. That means big expensive toys inside. You take the left side, I’ll take the right side. Seriously avoid the cake; it’s definitely a trap.” “A trap?” Bill said. “What kind of trap is it?” “The kind with radioactive frosting,” Molly said. “Last year I lost a shoe and my dignity to a sprinkle ambush at a stupid party. Ready?” Bill nodded. “Ready. But seriously, if a little toddler bites me again, I’m keeping every single present as hazard pay.” “Deal,” Molly said. “On three. One, two, three, go!”
created_at
"2026-09-03T16:16:38.998Z"
9/3/2026, 4:16:38 PM
model
"tencent/hy4-preview-20260827"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1926
moderation_latency
(null)
generation_time
239157
tokens_prompt
75
tokens_completion
15103
native_tokens_prompt
83
native_tokens_completion
17523
native_tokens_completion_images
(null)
native_tokens_reasoning
17237
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
0.043894245
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788452199-O2k6oYbGLMDB4lBHh0H9"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788452199-RObrz0qPivNkb5l5cXQO"
upstream_id
"a6e197d1-a4c0-428d-b062-fa2fe11b682f"
provider_responses
0
endpoint_id
"ad2a4093-3d2a-41d9-adf1-8b499ac8445d"
id
"a6e197d1-a4c0-428d-b062-fa2fe11b682f"
is_byok
false
latency
1926
model_permaslug
"tencent/hy4-preview-20260827"
provider_name
"Tencent"
status
200
total_cost
0.043894245
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: 90.00%, Deviation: 0.00%
neededClean
false
wordsTotal
200
wordsDialogue
180
100.0000%