NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0662EQ36YVB9Y0A16YYCB6
Run Details
Model:
Z.AI GLM 4.5 Air
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
9.0s
Cost:
$0.000710
Provider:
Z.AI
Evaluation summary
Score
Evaluator
Details Link
32.02%
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
Detective Miller arrived at the crime scene just after midnight, the rain lashing against his trench coat as he surveyed the dimly lit alley. The victim lay motionless near the dumpster, blood pooling on the wet pavement while nearby officers secured the perimeter. Miller knelt carefully beside the body, noting the victim's contorted expression and the single stab wound to the chest. The rain had washed away most footprints, but Miller spotted a distinctive heel print near the victim's right hand. His phone buzzed with an urgent message: the victim was a prominent businessman with many enemies and few friends. Miller's eyes caught something glinting in the victim's pocket - a small silver locket with a broken chain. The forensic team arrived, their flashlights cutting through the darkness as they began their meticulous search for clues. Miller noticed a discarded cigarette butt near the trash can, brand unfamiliar but expensive, perhaps a clue. As the first morning light began to creep in, Miller realized this murder was far more complicated than he initially thought. The victim's phone rang suddenly, startling everyone at the scene - the caller ID showing an unknown number.
created_at
"2026-04-24T16:46:49.314Z"
4/24/2026, 4:46:49 PM
model
"z-ai/glm-4.5-air"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1284
moderation_latency
(null)
generation_time
8403
tokens_prompt
46
tokens_completion
791
native_tokens_prompt
40
native_tokens_completion
639
native_tokens_completion_images
(null)
native_tokens_reasoning
492
native_tokens_cached
4
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"
usage
0.00071022
router
(null)
provider_responses
0
endpoint_id
"c8760514-8a81-4a73-ae2c-be4942ba93f3"
id
"20260425004649c1752624c33c4eb2"
is_byok
false
latency
1284
model_permaslug
"z-ai/glm-4.5-air"
provider_name
"Z.AI"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777049209-qdqOGJuy5PH1xBchqnAW"
session_id
(null)
api_type
"completions"
id
"gen-1777049209-EeyLLd7SLPKWQo3KGpqk"
upstream_id
"20260425004649c1752624c33c4eb2"
total_cost
0.00071022
cache_discount
6.8e-7
upstream_inference_cost
0
provider_name
"Z.AI"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
32.02%
Matches word count
n/a
neededClean
false
sentences
10
wordCounts
0
24
1
19
2
19
3
19
4
19
5
17
6
18
7
17
8
21
9
17