NC Bench
Overview
About
Tests
Models
Model
Z.AI GLM 4.5
Test
Dialogue tags
Scenario
Write 200 words with 10% dialogue
Run ID
2026-02-08-01KGYYTH2C1VB8HEEK12DXDY1E
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
The blueprint was spread across the stolen ‘My Little Pony’ tablecloth, a garish splash of pink against the grimy diner table. Molly tapped a stubby finger on a diagram of a bouncy castle. “In through the ‘Enchanted Forest’ obstacle course. It’s the weak point. The volunteer is always texting her boyfriend.” Bill, nursing a lukacide of lukewarm coffee, grunted in reply. He was meticulously polishing a pair of oversized clown shoes. “Distraction is key. You create the chaos, I’ll grab the goods. We have a three-minute window before the piñata break.” She slid a pair of sticky-fingered gloves across the table. “Remember, no crying children. It’s bad for business.” Bill finally looked up, a glint of manic glee in his eyes. “Presents, Molly. Think of the loot.” He slipped on a bright red nose. “Let’s go ruin some birthdays.”
created_at
"2026-02-08T15:44:51.442226+00:00"
Sunday, February 8th, 2026 at 3:44:51 PM GMT+00:00
model
"z-ai/glm-4.5"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2363
moderation_latency
(null)
generation_time
5484
tokens_prompt
61
tokens_completion
199
native_tokens_prompt
70
native_tokens_completion
200
native_tokens_completion_images
0
native_tokens_reasoning
0
native_tokens_cached
69
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
0.00044819
router
(null)
provider_responses
0
id
"330ae8c8177a5d3ad0abcddfbc9751ae"
status
200
is_byok
false
latency
2363
endpoint_id
"e4ada6ec-12e7-49c9-837c-398dee612403"
provider_name
"Novita"
model_permaslug
"z-ai/glm-4.5"
api_type
"completions"
id
"gen-1770565485-Av7UxiAbWZtiMvSHRnzq"
upstream_id
"330ae8c8177a5d3ad0abcddfbc9751ae"
total_cost
0.00044819
cache_discount
0.00003381
upstream_inference_cost
0
provider_name
"Novita"
Evaluation details
Result
Evaluator
Details
Meta Data
0.0000%
Matches word count
n/a
neededClean
false
words
141
0.0000%
Dialogue to Total Word Ratio
Ratio: 51.06%, Deviation: 41.06%
neededClean
false
wordsTotal
141
wordsDialogue
72
0.0000%