NC Bench
Overview
About
Tests
Models
Model
Z.AI GLM 4.6
Test
Dialogue tags
Scenario
Write 200 words with 50% dialogue
Run ID
2026-02-08-01KGYXG6E4Z5S70M0VWT2DHWVA
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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 peered through binoculars from the passenger seat. The backyard was a chaotic riot of streamers and screaming children, a sugar-fueled minefield. A small boy in a superhero cape ran past, clutching a juice box like a grenade. The loot, a glittering mountain of gifts, sat precariously by the open patio doors. It was almost too easy. “The target is a seven-year-old’s party,” Molly stated flatly. “The presents are the main payload.” “I’ve got eyes on the bouncy castle,” Bill whispered back. “That’s the secure vault. We’ll need a tactical approach.” “Negative on the vault. The real prize is by the fireplace. We go in soft.” “But the cake looks incredible, Molly. That’s a high-value asset right there.” Molly lowered the binoculars, fixing him with a deadpan stare. His focus was a liability, always drawn to the sugar instead of the score. “The piñata breaking is our signal. That’s the distraction. You create a scene at the snack table.” “A scene? You mean I actually get to eat the chips?” “Just try not to get frosting on the getaway car.” He grinned, reaching for the handle. Operation Birthday Cake was a go.
created_at
"2026-02-08T15:23:08.608043+00:00"
Sunday, February 8th, 2026 at 3:23:08 PM GMT+00:00
model
"z-ai/glm-4.6"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
260
moderation_latency
(null)
generation_time
89733
tokens_prompt
61
tokens_completion
4474
native_tokens_prompt
66
native_tokens_completion
4496
native_tokens_completion_images
(null)
native_tokens_reasoning
4120
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
0.0078402199999776
router
(null)
provider_responses
0
id
"chatcmpl-RPNQ2m8FWlb4jf38rdHRfT7T"
status
200
is_byok
false
latency
69
endpoint_id
"c8607edc-8577-4199-b03d-1213da4743dc"
provider_name
"DeepInfra"
model_permaslug
"z-ai/glm-4.6"
api_type
"completions"
id
"gen-1770564098-j87ERfTWXUuTD9Oufdrm"
upstream_id
"chatcmpl-RPNQ2m8FWlb4jf38rdHRfT7T"
total_cost
0.0078402199999776
cache_discount
0.0000112000000224
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
99.7443%
Matches word count
n/a
neededClean
false
words
196
99.9892%
Dialogue to Total Word Ratio
Ratio: 48.98%, Deviation: 1.02%
neededClean
false
wordsTotal
196
wordsDialogue
96
99.8667%