NC Bench
Overview
About
Tests
Models
Vendors
Model
Z.AI GLM 5
Test
Dialogue tags
Scenario
Write 200 words with 10% dialogue
Run ID
2026-02-11-01KH7H41AZXXTZ0FTJHGMMRN50
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
Bill adjusted his binoculars, the cheap plastic lenses fogging instantly from the sheer intensity of his gaze. Inside the community center, the target demographic was running wild. A sea of sugar-fueled six-year-olds spun in chaotic circles, entirely oblivious to the tactical extraction about to unfold. Molly checked her tactical watch, tapping the face with a gloved finger. She wore a utility vest that clung too tightly, brimming with tools better suited for a bank vault than a bouncy castle anniversary party. The sensory assault of screaming voices and popping balloons was overwhelming, creating a sonic barrier that only professionals would dare breach. "The clown is our greatest threat," Bill whispered, adjusting his grip. "I'll neutralize the funny man," Molly replied coldly. "Check," said Bill. The prize sat on a folding table near the back: a glittering mountain of wrapped boxes. It was high-stakes piracy involving Disney merchandise. Bill clicked his pen, a nervous habit picked up during his time inside. He calculated the trajectory of a rogue beach ball. This wasn't just a theft; it was a commando raid through a war zone of juice boxes. If they moved during the cake presentation, nobody would notice the two adults shoving gifts into a burlap sack. It was the perfect crime, assuming nobody noticed the getaway car was a minivan with a missing hubcap. They waited for the signal, two shadows against the wall.
created_at
"2026-02-11T23:41:14.764317+00:00"
Wednesday, February 11th, 2026 at 11:41:14 PM GMT+00:00
model
"z-ai/glm-5-20260211"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
361
moderation_latency
(null)
generation_time
167397
tokens_prompt
77
tokens_completion
4687
native_tokens_prompt
66
native_tokens_completion
4148
native_tokens_completion_images
(null)
native_tokens_reasoning
4321
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
0.0133396
router
(null)
provider_responses
0
id
"e48273474e35425f87d86fe9384f772a"
status
200
is_byok
false
latency
360
endpoint_id
"a3983e50-dec5-4453-80f6-8ab726493ca4"
provider_name
"Friendli"
model_permaslug
"z-ai/glm-5-20260211"
api_type
"completions"
id
"gen-1770853107-tHrgucMx5rimdJwk1bp2"
upstream_id
"e48273474e35425f87d86fe9384f772a"
total_cost
0.0133396
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
237
94.2334%
Dialogue to Total Word Ratio
Ratio: 5.06%, Deviation: 4.94%
neededClean
false
wordsTotal
237
wordsDialogue
12
47.1167%