NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1KZGH2TSNSDFQM70YZFMNDF
Run Details
Model:
Hy4 Preview (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
3m 19s
Cost:
$0.032707
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 and Bill crouched behind a plastic unicorn. The huge house pulsed with chaos. “Ready?” Molly asked. “Define ready,” Bill said. “I’m wearing an inflatable T-Rex suit with a tail I keep tripping over. If a toddler sees me, they’ll scream or demand a ride.” “You’re the distraction,” Molly said. “I’m the shadow. We slip in during the piñata chaos, grab the presents, and vanish.” “All the presents? There’s a mountain. Do we take the wrapped ones or the already-opened toys?” “Wrapped. Kids haven’t bonded yet. Lower guilt.” “What about the cake?” “Not on the list.” “Not one bite?” “Cake is a trap. Frosting is edible glue.” “Glue with sprinkles.” “Exactly. Stay focused.” “Molly, there’s a pony.” “The pony is a plot twist, Bill. Focus. You waddle in, yell ‘Piñata emergency,’ and I raid the gift table.” “Can I keep the pony?” “No. We are not stealing livestock today.” “Define livestock.” “Anything that poops in the getaway van.” “Fine.” “And if the birthday kid hugs me?” “You let them. Then you steal their soul and their LEGO.” “Harsh.” “Effective. On three. One—” “Wait, my tail’s caught in the—” “Bill, we discussed tail safety.” “You discussed. I ate a cupcake.” “Two.”
created_at
"2026-09-03T15:51:58.818Z"
9/3/2026, 3:51:58 PM
model
"tencent/hy4-preview-20260827"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1870
moderation_latency
(null)
generation_time
198748
tokens_prompt
75
tokens_completion
11794
native_tokens_prompt
83
native_tokens_completion
13050
native_tokens_completion_images
(null)
native_tokens_reasoning
12705
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
0.032707272
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788450718-3ZwWszUNKDpQgFCUzdwu"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788450718-3eJ8Eq1d4OpBXhrMqV3X"
upstream_id
"2e57d2ad-53ed-4b45-9530-9dbde6053d74"
provider_responses
0
endpoint_id
"ad2a4093-3d2a-41d9-adf1-8b499ac8445d"
id
"2e57d2ad-53ed-4b45-9530-9dbde6053d74"
is_byok
false
latency
1870
model_permaslug
"tencent/hy4-preview-20260827"
provider_name
"Tencent"
status
200
total_cost
0.032707272
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%