NC Bench
Overview
About
Tests
Models
Model
Z.AI GLM 4.6
Test
Dialogue tags
Scenario
Write 200 words with 10% dialogue
Run ID
2026-02-08-01KGYXCCB0KNEWMTTV6NA4FC78
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
The target sat glittering by the bouncy castle, a fortress of cardboard and curling ribbon. From their position behind the prize-winning zucchini patch, Molly surveyed the scene with professional disdain. The real security wasn’t the distracted parents grilling hot dogs; it was the horde of small, screaming sentinels, their faces smeared with a warpaint of chocolate and glee. They were unpredictable, dangerously fast, and fueled by pure, unadulterated sugar. A seismic tremor from the castle sent a shudder through the ground. Bill, beside her, adjusted the oversized canvas sack slung over his shoulder, making him look like a disheveled Santa who’d gotten lost. "Ready?" he whispered, nudging her with a bony elbow. "Give me a second," Molly hissed, swatting at a branch. "This shrubbery is incredibly itchy." He sighed, a long-suffering sound. "We have a window before the piñata." Molly nodded, her eyes fixed on the biggest prize, a box wrapped in unicorn paper that had to be at least three feet long. Extraction would be tricky, but the payoff—a living room filled with stolen loot—was worth the risk. She just hoped none of it was a drum set.
created_at
"2026-02-08T15:20:16.975646+00:00"
Sunday, February 8th, 2026 at 3:20:16 PM GMT+00:00
model
"z-ai/glm-4.6"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
261
moderation_latency
(null)
generation_time
42702
tokens_prompt
61
tokens_completion
2186
native_tokens_prompt
66
native_tokens_completion
2221
native_tokens_completion_images
(null)
native_tokens_reasoning
2006
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
0.0038817199999776
router
(null)
provider_responses
0
id
"chatcmpl-RR8ouIXjYbreH76PN8QnkjnM"
status
200
is_byok
false
latency
66
endpoint_id
"c8607edc-8577-4199-b03d-1213da4743dc"
provider_name
"DeepInfra"
model_permaslug
"z-ai/glm-4.6"
api_type
"completions"
id
"gen-1770563973-WfD4sHZTmeOj95lDDJ2f"
upstream_id
"chatcmpl-RR8ouIXjYbreH76PN8QnkjnM"
total_cost
0.0038817199999776
cache_discount
0.0000112000000224
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
97.6276%
Matches word count
n/a
neededClean
false
words
193
99.9798%
Dialogue to Total Word Ratio
Ratio: 8.81%, Deviation: 1.19%
neededClean
false
wordsTotal
193
wordsDialogue
17
98.8037%