NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-11-11-01M75MZ729A73WXX2G65EXB454
Run Details
Model:
Hy4 (Reasoning, High)
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
55.2s
Cost:
$0.007538
Provider:
Tencent
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
Model input
User/Human
Please write the opening scene of a murder mystery where each sentence has exactly 20 words. Please make sure that each sentence has the same length. Only return the opening itself.
Model response
Messages
Meta
AI
Rain stitched the windows of Wrenfield Manor while eleven guests pretended not to hear the clock stop at exactly midnight. In the locked library, a fire breathed low, and Lord Ashcombe lay beside the scattered chessmen, smiling at no one. A silver letter opener rested beneath his hand, clean as moonlight, though blood darkened his ivory cufflinks, waistcoat, and shirtfront. Inspector Vale arrived before the thunder, carrying a damp coat, a lantern, and an inconvenient memory of the house itself. No footprints crossed the wet terrace, yet one white rose lay freshly snapped across the threshold beneath the bolted door. Each guest offered an alibi as polished as the crystal, and each avoided the empty chair beside the murdered victim. Vale noticed the chessboard, where a black queen had been moved three squares after death by someone still listening nearby. He lifted his lantern, and across the sooty mirror, a message was written in a trembling hand: confess before dawn.
created_at
"2026-11-11T15:52:34.649Z"
11/11/2026, 3:52:34 PM
model
"tencent/hy4-20261104"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1090
moderation_latency
(null)
generation_time
55142
tokens_prompt
46
tokens_completion
6022
native_tokens_prompt
56
native_tokens_completion
6009
native_tokens_completion_images
(null)
native_tokens_reasoning
5801
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
0.007537606
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.22.2; linux; x64))"
http_referer
(null)
request_id
"req-1794412354-qBE8dZLf3qOCDsQZDmnG"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1794412354-JH088iNBqKsOzN7R0sea"
upstream_id
"a5c7f585-b811-4be5-b99f-cc6b8c83fbee"
provider_responses
0
endpoint_id
"b5b076de-19fd-4e5c-adc2-2420a425969e"
id
"a5c7f585-b811-4be5-b99f-cc6b8c83fbee"
is_byok
false
latency
1090
model_permaslug
"tencent/hy4-20261104"
provider_name
"Tencent"
status
200
total_cost
0.007537606
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
sentences
8
wordCounts
0
20
1
20
2
20
3
20
4
20
5
20
6
20
7
20