NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ012BPTXDRP5TRXRFXH2HXS
Run Details
Model:
Z.AI GLM 4.5 Air
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
12.1s
Cost:
$0.000694
Provider:
Z.AI
Evaluation summary
Score
Evaluator
Details Link
93.65%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
46.8248%
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 ski mask, the elastic biting into her hair. "Alright, Bill. The chaos is our cover. We slip in after the piƱata's broken. Parents are distracted, kids are sugar-crazed." She gestured towards the brightly decorated house, balloons bobbing in the breeze. "Target: the pile by the door. Grab and go. Five minutes max, tops. No heroics." Bill fiddled with his oversized gloves, eyeing a stray tricycle warily. "Five minutes? With that tiny terror in the Batman costume eyeing the loot like a hawk? Seems risky." He nudged a discarded party horn with his toe. "What if the clown shows early?" Molly sighed, pulling out a small, sleek tool. "Then we improvise. Focus, Bill. Remember, 'accidental' tripping near the presents is our distraction. You create the mess, I grab the bags. Simple." She peered through the front window, watching a toddler attempt to eat a cupcake sideways. "The presents look nice. Expensive wrapping paper... should be easy targets." Bill kicked the tricycle again. "Easy? Sounds like begging for a sugar-rush tantrum. My legs are shaky already." He straightened up. "Alright, let's do this. Just... don't leave me behind, yeah?"
created_at
"2026-04-24T15:17:24.836Z"
4/24/2026, 3:17:24 PM
model
"z-ai/glm-4.5-air"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2662
moderation_latency
(null)
generation_time
11998
tokens_prompt
77
tokens_completion
707
native_tokens_prompt
66
native_tokens_completion
623
native_tokens_completion_images
(null)
native_tokens_reasoning
407
native_tokens_cached
24
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
0.00069442
router
(null)
provider_responses
0
endpoint_id
"c8760514-8a81-4a73-ae2c-be4942ba93f3"
id
"2026042423172598c87c49f65449b9"
is_byok
false
latency
2662
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-1777043844-PGE7ogMT4k3w4FN3tuXO"
session_id
(null)
api_type
"completions"
id
"gen-1777043844-CMiTAGs7lkkrUXZ0zyAj"
upstream_id
"2026042423172598c87c49f65449b9"
total_cost
0.00069442
cache_discount
0.00000408
upstream_inference_cost
0
provider_name
"Z.AI"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
93.65%
Matches word count
n/a
neededClean
false
words
191
0.00%
Dialogue to Total Word Ratio
Ratio: 61.14%, Deviation: 51.14%
neededClean
false
wordsTotal
193
wordsDialogue
118
46.8248%