NC Bench
Overview
About
Tests
Models
Model
Z.AI GLM 4.7
Test
Dialogue tags
Scenario
Write 200 words with 10% dialogue
Run ID
2026-02-08-01KGZ05MC6W8Q5619CDJ0ADKFH
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 neon sombrero, squinting through the mesh eyeholes of a realistic llama costume. Bill struggled to zip up his matching purple suit, inhaling the scent of cheap polyester and moral decay. The target was a chaotic backyard filled with screaming six-year-olds, a fortress of sticky fingers. Their objective sat on a picnic table: a mountain of wrapped boxes containing gaming consoles and rare dolls. Bill checked his watch, sweat beading on his forehead beneath the hot afternoon sun. He looked terrified of the toddler mob. "Bill, tell me we are ready to go right now," Molly whispered. Molly nodded, checking the grappling hook hidden inside a hollowed-out piƱata. The plan required them to blend in as unpaid entertainment, create a diversion involving a spontaneously combusting cake, and abscond with the loot under a blanket of confusion. It was a risky play, but the payoff was worth the public shaming. They needed to strike fast before the professional clown arrived to twist balloons into animal shapes. That guy was a real professional. "I say we steal every single present in this yard," she commanded. The two llamas sprinted awkwardly toward the bouncy castle, ready to ruin childhoods forever. Nothing would stop them.
created_at
"2026-02-08T16:10:47.949494+00:00"
Sunday, February 8th, 2026 at 4:10:47 PM GMT+00:00
model
"z-ai/glm-4.7-20251222"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1333
moderation_latency
(null)
generation_time
149153
tokens_prompt
61
tokens_completion
6659
native_tokens_prompt
66
native_tokens_completion
6682
native_tokens_completion_images
(null)
native_tokens_reasoning
6425
native_tokens_cached
2
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
0.01473902
router
(null)
provider_responses
0
id
"20260209000818739bc25afbb7416d"
status
200
is_byok
false
latency
1333
endpoint_id
"be4acbf5-9fcf-4332-a01d-76dfeb6d7b99"
provider_name
"Z.AI"
model_permaslug
"z-ai/glm-4.7-20251222"
api_type
"completions"
id
"gen-1770566898-9E1DmwJCYNtUJE70hLTz"
upstream_id
"20260209000818739bc25afbb7416d"
total_cost
0.01473902
cache_discount
9.8e-7
upstream_inference_cost
0
provider_name
"Z.AI"
Evaluation details
Result
Evaluator
Details
Meta Data
98.7124%
Matches word count
n/a
neededClean
false
words
206
99.9999%
Dialogue to Total Word Ratio
Ratio: 9.71%, Deviation: 0.29%
neededClean
false
wordsTotal
206
wordsDialogue
20
99.3561%