NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-02-01M1GVSW6YGZJXCZRVK92FV8SV
Run Details
Model:
Z.AI GLM 5.3 (Reasoning, Max)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
57.9s
Cost:
$0.013729
Provider:
Z.AI
Evaluation summary
Score
Evaluator
Details Link
99.74%
Matches word count
(details)
97.17%
Dialogue to Total Word Ratio
(details)
98.4553%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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
"You got the floor plan?" Molly asked. "Photographed it when I dropped off my nephew," Bill said. "Living room, kitchen, presents on the gift table beside the sliding door." "The sliding door with the bouncy castle directly outside it?" "That's not an obstacle. That's an escape route." "Bill, it's a bouncy castle." "You bounce, you vault, you're over the fence in seconds. Kids do it constantly." "Kids weigh forty pounds! You'll bottom out and they'll have to rescue you with a spatula." "Fine. Plan B. We go in as the entertainment. I bought a magician's outfit." "You can't do magic." "I don't need to do magic. I need to look like a man who's seen magic done. Watch." He palmed a sugar packet. "Nothing up my sleeve." "Where'd the sugar go?" "That's the trick. Nobody knows. That's showmanship." "Breathtaking. Okay, new plan. We wait for the piñata. Every adult looks at the piñata. Every adult has always looked at the piñata. It's a psychological weakness built into parents." Molly nodded slowly. "That's actually clean." "We grab the table and we're gone before the candy hits the grass." "What about the birthday boy?" "He's five. His memory is a goldfish. By nap time, we're legends."
created_at
"2026-09-02T10:49:27.528Z"
9/2/2026, 10:49:27 AM
model
"z-ai/glm-5.3-20260816"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3327
moderation_latency
(null)
generation_time
57740
tokens_prompt
75
tokens_completion
2764
native_tokens_prompt
73
native_tokens_completion
3097
native_tokens_completion_images
(null)
native_tokens_reasoning
2802
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
num_fetches
(null)
web_search_engine
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
service_tier
(null)
usage
0.013729
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788346167-2Pf55KdaTv3XaPACncEk"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788346167-vjezqAKjQSntZQvpRLwl"
upstream_id
"202609021849277a84a9a1dc794a9d"
provider_responses
0
endpoint_id
"db975786-e7f6-4838-9e56-3e0b77f1bdc2"
id
"202609021849277a84a9a1dc794a9d"
is_byok
false
latency
3327
model_permaslug
"z-ai/glm-5.3-20260816"
provider_name
"Z.AI"
status
200
total_cost
0.013729
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Z.AI"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
99.74%
Matches word count
n/a
neededClean
false
words
204
97.17%
Dialogue to Total Word Ratio
Ratio: 94.12%, Deviation: 4.12%
neededClean
false
wordsTotal
204
wordsDialogue
192
98.4553%