NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1M154V802Z44RJV3R1R7F1V
Run Details
Model:
Hy4 Preview (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
3m 19s
Cost:
$0.033993
Provider:
Tencent
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.9920%
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
Outside the party, Molly and Bill huddled in their van. Molly: "Okay, Bill, here's the plan. We sneak into the birthday party dressed as clowns, because nothing says 'trusted professional' like oversized shoes, a red nose, and a criminal record." Bill: "Right. And while the sugar-crazed kids are hypnotized by the magician, we slip into the gift room and stuff every present into our extra-large piñata." Molly: "A piñata? Bill, we can't smash open our escape vehicle. It's papier-mâché, not bulletproof." Bill: "Fine. We'll use the ball pit as a decoy. Kids dive in, we toss the presents out the window into the getaway stroller." Molly: "A stroller? We're stealing a mountain of toys, not going for a leisurely jog. We need the minivan." Bill: "The minivan has a car seat in it, Molly. Do you have any idea how hard it is to hotwire a vehicle with a juice box holder?" Molly: "Then we bribe the toddler with the best loot: the noisy drum set." Bill: "Brilliant. He'll scream, parents panic, and we waltz out wearing party hats and holding garbage bags labeled 'Leftover Cake.'" Molly: "Nobody questions cake. Just don't eat the evidence." Bill: "Don't worry. I'm allergic to fun."
created_at
"2026-09-03T16:20:42.993Z"
9/3/2026, 4:20:42 PM
model
"tencent/hy4-preview-20260827"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1741
moderation_latency
(null)
generation_time
199266
tokens_prompt
75
tokens_completion
11660
native_tokens_prompt
83
native_tokens_completion
13564
native_tokens_completion_images
(null)
native_tokens_reasoning
13251
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
0.033992786
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788452442-cQ4yj2quOfLajyK0KeW3"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788452442-2N1QNUS7ZHCLPrVBVNi2"
upstream_id
"6ea557a3-5bb3-4295-8485-0222e4ebf3a9"
provider_responses
0
endpoint_id
"ad2a4093-3d2a-41d9-adf1-8b499ac8445d"
id
"6ea557a3-5bb3-4295-8485-0222e4ebf3a9"
is_byok
false
latency
1741
model_permaslug
"tencent/hy4-preview-20260827"
provider_name
"Tencent"
status
200
total_cost
0.033992786
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
99.98%
Matches word count
n/a
neededClean
false
words
202
100.00%
Dialogue to Total Word Ratio
Ratio: 90.20%, Deviation: 0.20%
neededClean
false
wordsTotal
204
wordsDialogue
184
99.9920%