NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-06-24-01KVX3C2BFWX9Y36PB3JNJJN64
Run Details
Model:
Z.AI GLM 5.2 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
31.4s
Cost:
$0.008986
Provider:
Z.AI
Evaluation summary
Score
Evaluator
Details Link
95.99%
Matches word count
(details)
73.66%
Dialogue to Total Word Ratio
(details)
84.8228%
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
"Bill, put down the lockpicks. We’re walking through the front door." "Molly, it’s a seven-year-old’s birthday party, not a casino." "Exactly. Security is a tired mom and a bounce house. We just need a cover." "What cover? We’re forty and wearing black turtlenecks in July." "We’re caterers, Bill. Grab the folding tables." "We don't have any food." "Then we're the entertainment." "You’re gonna put on a clown nose?" "Worse. I'm the balloon artist. You're my silent assistant." "You don't know how to make balloon animals." "I watched a twelve-minute tutorial in the van. I can make a snake." "A snake. At a kid's party. What happens when they ask for a poodle?" "I make a thick snake and call it a dehydrated poodle. Listen, while they're distracted by my terrifying balloon creations, you empty the gift table into the sack." "The gift table next to the cake?" "Yes." "The cake guarded by a piñata?" "Bill, it's paper mache. If it gets aggressive, you have a crowbar." "I'm not fighting a donkey for a Hungry Hungry Hippos game." "Just grab the Lego sets, Bill. We're retiring to Aruba." He sighed, adjusting his turtleneck.
created_at
"2026-06-24T15:18:25.915Z"
6/24/2026, 3:18:25 PM
model
"z-ai/glm-5.2-20260616"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3390
moderation_latency
(null)
generation_time
31207
tokens_prompt
77
tokens_completion
2036
native_tokens_prompt
73
native_tokens_completion
2019
native_tokens_completion_images
(null)
native_tokens_reasoning
1736
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
0.0089858
router
(null)
provider_responses
0
endpoint_id
"442ea97f-ad5e-40d5-b9a6-66e9e0417dce"
id
"20260624231826e0b70f53f1b24dd2"
is_byok
false
latency
3390
model_permaslug
"z-ai/glm-5.2-20260616"
provider_name
"Z.AI"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.16.0; linux; x64))"
http_referer
(null)
request_id
"req-1782314305-0LuxwycEVOjXzSeh0HJZ"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1782314305-lEZGMfiJ8NkmaNPFRShQ"
upstream_id
"20260624231826e0b70f53f1b24dd2"
total_cost
0.0089858
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Z.AI"
response_cache_source_id
(null)
data_region
"global"
Evaluation details
Result
Evaluator
Details
Meta Data
95.99%
Matches word count
n/a
neededClean
false
words
192
73.66%
Dialogue to Total Word Ratio
Ratio: 97.44%, Deviation: 7.44%
neededClean
false
wordsTotal
195
wordsDialogue
190
84.8228%