NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1KXPRMJ9EJ96Z1T8F88F7G0
Run Details
Model:
Hy4 Preview (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
5m 17s
Cost:
$0.054934
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 pointed. “Phase one: we enter as entertainment. Phase two: I juggle, you wrangle toddlers, and we strip the gift table like a sale.” Bill groaned. “I’m not wrangling toddlers. Last time one used my trousers as a climbing wall and another stole my wallet.” “That’s excellent training,” Molly said. “You already know the enemy.” “The enemy is six and hyped on cake,” Bill replied. “They have sticky hands and zero fear. We should rob a bank.” “Banks have cameras,” Molly said. “This party has a piñata and a distracted dad. Now, you’ll wear the dinosaur suit.” “Why me?” Bill asked. “Because you’re the right height,” Molly said. “And because you look ridiculous. Also, you have the legs for it.” “I have great legs.” “In a suit with a tail, sure. The mum at the door will ask for a password. It’s ‘glitter’.” “Glitter?” “Say it with confidence. Then distract her by pointing at the cake. I’ll grab the presents while she’s distracted.” Bill sighed. “Fine. But if a child asks me to roar, I’m charging extra. If they hug me, double.” “Roar all you want,” Molly said. “Just roar while you load the presents into the van.” They grinned.
created_at
"2026-09-03T15:20:26.009Z"
9/3/2026, 3:20:26 PM
model
"tencent/hy4-preview-20260827"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1748
moderation_latency
(null)
generation_time
316872
tokens_prompt
75
tokens_completion
18572
native_tokens_prompt
83
native_tokens_completion
21937
native_tokens_completion_images
(null)
native_tokens_reasoning
21633
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
0.054933659
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788448826-3moJhL3JSPEb4Ldq3hEP"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788448826-sIJssvMNOQEc28yw7IMk"
upstream_id
"0f8f40e9-eddc-4d98-9275-429008664d66"
provider_responses
0
endpoint_id
"ad2a4093-3d2a-41d9-adf1-8b499ac8445d"
id
"0f8f40e9-eddc-4d98-9275-429008664d66"
is_byok
false
latency
1747
model_permaslug
"tencent/hy4-preview-20260827"
provider_name
"Tencent"
status
200
total_cost
0.054933659
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%