NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-02-08-01KGYXMYCDN3CW2MVE9E1VK2E0
Run Details
Model:
Z.AI GLM 4.5
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
5.7s
Cost:
$0.000571
Provider:
Novita
Evaluation summary
Score
Evaluator
Details Link
14.30%
Matches word count
(details)
95.96%
Dialogue to Total Word Ratio
(details)
55.1322%
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 the itchy feather of her parrot costume, the plastic beak obscuring her already limited view. Across the grimy van, Bill struggled to zip up his bulbous, green dinosaur suit, the zipper catching on the foam belly. Their surveillance of the party, a chaotic whirlwind of screaming children and stressed parents, was a masterclass in overstimulation. The target was a mountain of gifts, a glittering pyramid of cardboard and ribbon, left unguarded while a man in a bright blue wig attempted to make balloon animals. Bill’s muffled voice escaped from the depths of his tyrannosaurus head. “It’s a perfect target. Soft, over-caffeinated security.” Molly nodded, her own costume head wobbling precariously. The plan was simple: blend in, befriend the birthday boy, and start loading the “goodie bags” with the real loot. Bill had insisted on a smoke machine for their distraction, which Molly felt was a bit dramatic for a six-year-old’s party. The main obstacle was a hyperactive golden retriever, who seemed to view them not as fellow partygoers, but as two very large, suspiciously shaped chew toys.
created_at
"2026-02-08T15:24:20.048424+00:00"
2/8/2026, 3:24:20 PM
model
"z-ai/glm-4.5"
4/5/2001, 12:00:00 AM
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1554
moderation_latency
(null)
generation_time
5581
tokens_prompt
61
tokens_completion
242
native_tokens_prompt
70
native_tokens_completion
246
native_tokens_completion_images
0
native_tokens_reasoning
0
native_tokens_cached
24
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.00057144
router
(null)
provider_responses
0
id
"98ad36001732b9f58a023d560887f765"
status
200
is_byok
false
latency
1554
endpoint_id
"e4ada6ec-12e7-49c9-837c-398dee612403"
provider_name
"Novita"
model_permaslug
"z-ai/glm-4.5"
4/5/2001, 12:00:00 AM
api_type
"completions"
id
"gen-1770564254-bDwH1IquselMKQsnXmv4"
upstream_id
"98ad36001732b9f58a023d560887f765"
total_cost
0.00057144
cache_discount
0.00001176
upstream_inference_cost
0
provider_name
"Novita"
Evaluation details
Result
Evaluator
Details
Meta Data
14.30%
Matches word count
n/a
neededClean
false
words
179
95.96%
Dialogue to Total Word Ratio
Ratio: 5.49%, Deviation: 4.51%
neededClean
false
wordsTotal
182
wordsDialogue
10
55.1322%