NC Bench
Overview
About
Tests
Models
Vendors
Model
Z.AI GLM 5
Test
Dialogue tags
Scenario
Write 200 words with 10% dialogue
Run ID
2026-02-11-01KH7H9PZX03PSRQ60DTECNTVY
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 adjusted the binoculars, the plastic rim digging into her eye sockets. Through the window, the enemy was assembling. Tiny, sticky humans ran in circles, fueled by sugar and malice. A banner reading "Happy 5th Birthday, Timmy" hung crookedly above the cake table, which was currently serving as a staging ground for the prize: a mountain of wrapped boxes. The intel suggested a gaming console and a premium bicycle were among the assets. She sketched a tactical diagram on a crumpled coffee cup, outlining the perimeter. The primary obstacle wasn't the alarm system, which was surprisingly archaic, but the erratic movement of the hostiles. A clown twisted balloons into sword shapes near the entry point, creating a natural chokepoint. "We go in when they cut the cake," Molly whispered. Bill shifted in the driver's seat, looking through the windshield with a furrowed brow. He tapped his fingers on the steering wheel, a nervous tic he had developed since their last job at the retirement home went sideways. The guilt of stealing bingo prizes still weighed heavy on his conscience. "Are we the bad guys here?" Bill asked softly. "Only if we get caught," she replied sharply. The plan was solid. They would breach the side gate while the children were blindfolded, swap the present pile with decorative rocks, and vanish into the suburban night. It was a victimless crime, assuming Timmy didn't have a security detail.
created_at
"2026-02-11T23:44:19.25835+00:00"
Wednesday, February 11th, 2026 at 11:44:19 PM GMT+00:00
model
"z-ai/glm-5-20260211"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
745
moderation_latency
(null)
generation_time
165641
tokens_prompt
77
tokens_completion
2625
native_tokens_prompt
66
native_tokens_completion
2357
native_tokens_completion_images
(null)
native_tokens_reasoning
2258
native_tokens_cached
0
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
0.0076084
router
(null)
provider_responses
0
id
"cddc0ceab2ca41499d5eb88e4baa343f"
status
200
is_byok
false
latency
745
endpoint_id
"a3983e50-dec5-4453-80f6-8ab726493ca4"
provider_name
"Friendli"
model_permaslug
"z-ai/glm-5-20260211"
api_type
"completions"
id
"gen-1770853293-JPSTgPA9XECnDtQ3soqc"
upstream_id
"cddc0ceab2ca41499d5eb88e4baa343f"
total_cost
0.0076084
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Friendli"
Evaluation details
Result
Evaluator
Details
Meta Data
0.0000%
Matches word count
n/a
neededClean
false
words
236
100.0000%
Dialogue to Total Word Ratio
Ratio: 9.75%, Deviation: 0.25%
neededClean
false
wordsTotal
236
wordsDialogue
23
50.0000%