NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ01CFAXC9V6B5XXMNFPSC7N
Run Details
Model:
Z.AI GLM 4.5 Air
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
22.0s
Cost:
$0.000593
Provider:
Z.AI
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.0000%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 adjusted her black balaclava, peering through a gap in the hedge. The back garden was a riot of primary colours and chaotic energy. Bill fidgeted beside her, nearly knocking over a gnome. "Too many kids," he whispered, voice muffled. "They're like sticky landmines." Molly ignored him, scanning the buffet table piled high with suspiciously bright cupcakes. "Presents are in the garage," she breathed, pointing. "Weak lock. Easy grab." Bill watched a toddler trip over a stray toy car, sending streamers flying. "Timing's crucial," Molly continued, calculating angles. "When the magician starts the rabbit trick, chaos erupts. We slip in, grab, slip out. No noise." Bill nodded, wiping sweat with his sleeve. "What if the rabbit bites?" Molly shot him a withering look. "Bill, focus. Just... watch where you step." The magician flourished, pulling out a squeaky rubber chicken. Bill groaned. "This is gonna be a disaster." Molly tightened her grip on the sack. "Ready?" Bill took a deep, shaky breath. "As I'll ever be."
created_at
"2026-04-24T15:22:56.237Z"
4/24/2026, 3:22:56 PM
model
"z-ai/glm-4.5-air"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2589
moderation_latency
(null)
generation_time
11687
tokens_prompt
77
tokens_completion
585
native_tokens_prompt
66
native_tokens_completion
530
native_tokens_completion_images
(null)
native_tokens_reasoning
328
native_tokens_cached
18
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
0.00059314
router
(null)
provider_responses
0
endpoint_id
"90fc9bb3-01bb-419f-bb58-dea60a80d201"
is_byok
false
latency
91
model_permaslug
"z-ai/glm-4.5-air"
provider_name
"Novita"
status
429
1
endpoint_id
"f7dc79ca-bbbd-41a1-8eef-616d981ff1cb"
is_byok
false
latency
10077
model_permaslug
"z-ai/glm-4.5-air"
provider_name
"SiliconFlow"
status
504
2
endpoint_id
"c8760514-8a81-4a73-ae2c-be4942ba93f3"
id
"202604242323067779b791d6a648f9"
is_byok
false
latency
2589
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-1777044176-nMtVWQsgejNZnI6GXlLG"
session_id
(null)
api_type
"completions"
id
"gen-1777044176-blJ2HrajAc8zhxg5mVkJ"
upstream_id
"202604242323067779b791d6a648f9"
total_cost
0.00059314
cache_discount
0.00000306
upstream_inference_cost
0
provider_name
"Z.AI"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
165
0.00%
Dialogue to Total Word Ratio
Ratio: 35.15%, Deviation: 25.15%
neededClean
false
wordsTotal
165
wordsDialogue
58
0.0000%