NC Bench
Overview
About
Tests
Models
Model
Z.AI GLM 4.6
Test
Dialogue tags
Scenario
Write 200 words with 50% dialogue
Run ID
2026-02-08-01KGYZDX97CXEGDJF915R7CD2E
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
Bill adjusted the binoculars, the vinyl of the driver's seat sticking to his back. Across the street, a chaotic rainbow of bouncy castle and streamers marked the target’s location. A small horde of sugar-fueled seven-year-olds swarmed a man in a top hat, who was attempting to pull a never-ending scarf from his sleeve. Molly, beside him, sketched a crude map on a napkin, her expression grim. She circled the patio table, a veritable mountain of gaily wrapped loot. The prize. Bill lowered the binoculars, a flicker of doubt crossing his face. He’d cracked safes with less emotional baggage. “The magician is our distraction,” Molly whispered, pointing a pen. “When he makes the dove appear, that’s our signal. We move.” Bill snorted. “You want us to run through a minefield of offspring and sticky fingers for a bunch of Lego sets?” “It’s not Lego, it’s ‘Glimmer-Gems Unicorn Construction,’” she corrected, her voice tight. “The intel says the big box from Grandma Carol is the mother lode.” Bill peered again. “The one wrapped in cartoon puppies? Mols, we’re stealing a child's birthday. That’s not a heist, that’s a reason to go to hell.”
created_at
"2026-02-08T15:56:15.828076+00:00"
Sunday, February 8th, 2026 at 3:56:15 PM GMT+00:00
model
"z-ai/glm-4.6"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
247
moderation_latency
(null)
generation_time
54796
tokens_prompt
61
tokens_completion
1748
native_tokens_prompt
66
native_tokens_completion
1757
native_tokens_completion_images
(null)
native_tokens_reasoning
1547
native_tokens_cached
64
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
0.0030631599999552
router
(null)
provider_responses
0
id
"chatcmpl-RpcGqDqDhrFbdP51a4wMgvwe"
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-1770566120-58eAWI11EWzs5YfGHXqa"
upstream_id
"chatcmpl-RpcGqDqDhrFbdP51a4wMgvwe"
total_cost
0.0030631599999552
cache_discount
0.0000224000000448
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
99.3769%
Matches word count
n/a
neededClean
false
words
195
36.7879%
Dialogue to Total Word Ratio
Ratio: 40.00%, Deviation: 10.00%
neededClean
false
wordsTotal
195
wordsDialogue
78
68.0824%