NC Bench
Overview
About
Tests
Models
Model
Z.AI GLM 4.6
Test
Dialogue tags
Scenario
Write 200 words with 50% dialogue
Run ID
2026-02-08-01KGYZ201D6KC666EPX8Z838XX
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 slapped the blueprints onto the van’s dashboard. The paper was crinkled and smelled faintly of fruit punch. Bill nervously eyed the suburban house, where the distant, horrifying sound of a “Baby Shark” remix echoed. A sad-looking clown statue on the lawn seemed to be watching them with its one good eye. “Right,” Molly said, tapping a drawing of a bouncy castle. “Phase one: infiltration through the ‘Dragon’s Den.’ We have a two-minute window before the cake-cutting.” Bill winced. “What about the security? The toddler with the sticky fingers? He leaves prints everywhere.” She slid a pair of latex gloves across the seat. “That’s what these are for, genius. We go in, grab the loot, and we’re out before anyone can say ‘pass the juice box.’” Bill fumbled with the gloves, his hands sweating profusely. “And the escape route?” he mumbled, pulling one on with a wet snap. “Is it clear of the ‘drop-off’ parent? My cousin Brenda gets real chatty.” Molly slammed her palm on the horn. “The presents, Bill! Focus on the giant, shiny presents!”
created_at
"2026-02-08T15:50:14.089308+00:00"
Sunday, February 8th, 2026 at 3:50:14 PM GMT+00:00
model
"z-ai/glm-4.6"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
391
moderation_latency
(null)
generation_time
83155
tokens_prompt
61
tokens_completion
2453
native_tokens_prompt
66
native_tokens_completion
2460
native_tokens_completion_images
(null)
native_tokens_reasoning
2238
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
0.0042975799999776
router
(null)
provider_responses
0
id
"chatcmpl-R5FHdnVNRB6at1YMxXJAT9sl"
status
200
is_byok
false
latency
63
endpoint_id
"c8607edc-8577-4199-b03d-1213da4743dc"
provider_name
"DeepInfra"
model_permaslug
"z-ai/glm-4.6"
api_type
"completions"
id
"gen-1770565730-ceHQNSXMS25aF5MewWXJ"
upstream_id
"chatcmpl-R5FHdnVNRB6at1YMxXJAT9sl"
total_cost
0.0042975799999776
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
97.7388%
Dialogue to Total Word Ratio
Ratio: 46.11%, Deviation: 3.89%
neededClean
false
wordsTotal
180
wordsDialogue
83
58.9642%