NC Bench
Overview
About
Tests
Models
Model
Z.AI GLM 4.6
Test
Dialogue tags
Scenario
Write 200 words with 10% dialogue
Run ID
2026-02-08-01KGYZRQTR1S306C55559V7X2G
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 hunched over the schematic, a crayon drawing of 123 Maple Lane that smelled of orange juice and betrayal. The van’s interior lights cast long shadows across her face as she detailed the operation. Infiltration would be via the bouncy castle in the backyard, a noisy but effective vector. The primary sensory diversion was scheduled for 3:15 PM: “Pin the Tail on the Donkey.” That was their window. She pointed a grubby fingernail at a cluster of gift-bagged squares on the diagram. The payload. Bill, her accomplice, listened intently, chewing on a toothpick. He’d been casing the joint all morning, posing as a dog walker. He knew the layout, the guard rotations, the weak points. He finally spoke, his voice a low rumble. "But the glitter paper is a forensic nightmare." Molly didn’t even look up from the drawing. She simply reached into her duffel bag and produced a roll of industrial-strength lint rollers, holding them up like a trophy. "I've packed the industrial-grade lint rollers." The plan was flawless.
created_at
"2026-02-08T16:02:47.34112+00:00"
Sunday, February 8th, 2026 at 4:02:47 PM GMT+00:00
model
"z-ai/glm-4.6"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
240
moderation_latency
(null)
generation_time
90992
tokens_prompt
61
tokens_completion
2801
native_tokens_prompt
66
native_tokens_completion
2811
native_tokens_completion_images
(null)
native_tokens_reasoning
2640
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
0.0049083199999776
router
(null)
provider_responses
0
id
"chatcmpl-R0flvSazcGSSkX5hyLx5k2qV"
status
200
is_byok
false
latency
53
endpoint_id
"c8607edc-8577-4199-b03d-1213da4743dc"
provider_name
"DeepInfra"
model_permaslug
"z-ai/glm-4.6"
api_type
"completions"
id
"gen-1770566475-PDcBHOXCaY30h9BUUzc1"
upstream_id
"chatcmpl-R0flvSazcGSSkX5hyLx5k2qV"
total_cost
0.0049083199999776
cache_discount
0.0000112000000224
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
0.4920%
Matches word count
n/a
neededClean
false
words
173
99.7910%
Dialogue to Total Word Ratio
Ratio: 12.14%, Deviation: 2.14%
neededClean
false
wordsTotal
173
wordsDialogue
21
50.1415%