NC Bench
Overview
About
Tests
Models
Model
Z.AI GLM 4.6
Test
Dialogue tags
Scenario
Write 200 words with 10% dialogue
Run ID
2026-02-08-01KGYYDYSRWB6D3V404VF0SN0N
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 smoothed the crinkled blueprint of the Miller’s backyard across the van’s hood. The air, thick with the scent of impending cake, felt heavy. Her gloved finger traced the wobbly perimeter of the dinosaur-shaped bouncy castle, a primary obstacle. Its unpredictable undulations could throw a man off-balance, exposing him to the real enemy: sugar-fueled seven-year-olds with no concept of operational security. Bill, meticulously calibrating a high-powered party horn, nodded gravely. “What’s the play for the bouncy castle?” he asked, his voice a low whisper. “We avoid it. Too unstable.” “And what about the parents?” “The piñata is our key distraction.” Molly’s gaze shifted to the gift table, a glittering payload of presents wrapped in cartoon rocket ship paper. The piñata, a rainbow-striped unicorn, hung from a tree branch like a fragile, candy-filled bomb. A single, well-aimed rock from Bill’s slingshot would create a shower of cheap candy and glorious chaos, providing the perfect cover for them to snatch the goods and exfiltrate via the side gate. It was a flawless plan.
created_at
"2026-02-08T15:38:55.881395+00:00"
Sunday, February 8th, 2026 at 3:38:55 PM GMT+00:00
model
"z-ai/glm-4.6"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
460
moderation_latency
(null)
generation_time
61638
tokens_prompt
61
tokens_completion
2882
native_tokens_prompt
66
native_tokens_completion
2903
native_tokens_completion_images
(null)
native_tokens_reasoning
2825
native_tokens_cached
32
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
0.0050683999999776
router
(null)
provider_responses
0
id
"chatcmpl-RBMU3Nn252GHODqET4AuKcg1"
status
200
is_byok
false
latency
61
endpoint_id
"c8607edc-8577-4199-b03d-1213da4743dc"
provider_name
"DeepInfra"
model_permaslug
"z-ai/glm-4.6"
api_type
"completions"
id
"gen-1770565073-f7dWLL9eC8rR2moF1pci"
upstream_id
"chatcmpl-RBMU3Nn252GHODqET4AuKcg1"
total_cost
0.0050683999999776
cache_discount
0.0000112000000224
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
20.1897%
Matches word count
n/a
neededClean
false
words
180
99.4064%
Dialogue to Total Word Ratio
Ratio: 12.78%, Deviation: 2.78%
neededClean
false
wordsTotal
180
wordsDialogue
23
59.7980%