NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-06-24-01KVX2W370G8A21JBM4Z7FNPT2
Run Details
Model:
Z.AI GLM 5.2 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
1m 12s
Cost:
$0.024223
Provider:
Z.AI
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
99.96%
Dialogue to Total Word Ratio
(details)
99.9370%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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 her black turtleneck in the azalea bushes, squinting at the festive chaos unfolding across the manicured lawn. Bill crouched beside her, gripping a comically oversized sack that currently held nothing but his own misguided optimism. The vibrant sounds of pop music and shrieking children drifted through the glass. A towering mountain of brightly wrapped boxes sat unguarded near the punch bowl, practically begging to be stolen. Bill smeared a bit of grease under his eye, trying to look tactical but succeeding only in looking like a tired panda. Molly checked her watch, sighed, and prepared for absolute disaster. "Are you absolutely sure about this?" "It is a goldmine, Molly. They are just kids." "They are ruthless kids. Did you see the bouncy castle?" "We enter the kitchen. Grab the loot. Blend with the clowns." "You look nothing like a clown." "I have a nose." "That is a tomato." "We hit the gift table during the magic show. I will create a distraction." "By doing what exactly?" "I will pull a rabbit out of a hat." "You have no hat. Or rabbit." "I have a sock. And a pigeon. It works." "If we get mauled by sugar-crazed seven-year-olds, I am blaming you."
created_at
"2026-06-24T15:09:42.508Z"
6/24/2026, 3:09:42 PM
model
"z-ai/glm-5.2-20260616"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3194
moderation_latency
(null)
generation_time
72129
tokens_prompt
77
tokens_completion
4470
native_tokens_prompt
73
native_tokens_completion
5482
native_tokens_completion_images
(null)
native_tokens_reasoning
5217
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
0.024223
router
(null)
provider_responses
0
endpoint_id
"442ea97f-ad5e-40d5-b9a6-66e9e0417dce"
id
"20260624230942550ddfd3b5ec4fe5"
is_byok
false
latency
3194
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-1782313782-jypz7DrL7GsvvVftQpIp"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1782313782-ruNIV2xqfkC2riqXCKdE"
upstream_id
"20260624230942550ddfd3b5ec4fe5"
total_cost
0.024223
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
99.92%
Matches word count
n/a
neededClean
false
words
203
99.96%
Dialogue to Total Word Ratio
Ratio: 51.46%, Deviation: 1.46%
neededClean
false
wordsTotal
206
wordsDialogue
106
99.9370%