NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-02-01M1GTK634NQXCGWTHG0TAXXD4
Run Details
Model:
Z.AI GLM 5.3 (Reasoning, Max)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
38.3s
Cost:
$0.007195
Provider:
Z.AI
Evaluation summary
Score
Evaluator
Details Link
98.71%
Matches word count
(details)
94.06%
Dialogue to Total Word Ratio
(details)
96.3854%
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
Molly spread the crayon-drawn blueprint across the kitchen table. "You're telling me the getaway vehicle is a hatchback?" "It's a hybrid, Molly. Greenhouse gases matter, even in crime." "Fine. What about entry?" "We pose as entertainment. I'm a balloon artist." "You can't make balloons." "I can make a snake. Which is technically a worm with confidence." "And me?" "You're the face painter." "I don't paint faces." "You'll paint a butterfly on a six-year-old's cheek or we leave empty-handed. Them's the rules." "Bill, it's a children's birthday party. What's the security?" "A golden retriever named Biscuit and a dad in cargo shorts." "Armed?" "He has a hose." "Then we go loud. In, grab the presents, out in ninety seconds." "Subtle, Molly. It's a party, not a bank." "Fine. We stay for cake, blend in, then strike during the piñata." "That's actually genius. Everyone watches the piñata." "Nobody guards the gift table during a piñata." "One problem." "What?" "The blindfold makes me dizzy. I'll swing at a toddler." "Then you hold the presents and I swing." "You're a natural-born leader, you know that?" "Shut up and eat your surveillance donuts. We move at two. Nap time."
created_at
"2026-09-02T10:28:19.692Z"
9/2/2026, 10:28:19 AM
model
"z-ai/glm-5.3-20260816"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
5600
moderation_latency
(null)
generation_time
38261
tokens_prompt
75
tokens_completion
1584
native_tokens_prompt
73
native_tokens_completion
1612
native_tokens_completion_images
(null)
native_tokens_reasoning
1318
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
0.007195
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788344899-RhZL4f9Chumnbrqp4Dfu"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788344899-AGEMWyKtczxtwF8xczyH"
upstream_id
"2026090218281979f3f889654b4f76"
provider_responses
0
endpoint_id
"db975786-e7f6-4838-9e56-3e0b77f1bdc2"
id
"2026090218281979f3f889654b4f76"
is_byok
false
latency
5600
model_permaslug
"z-ai/glm-5.3-20260816"
provider_name
"Z.AI"
status
200
total_cost
0.007195
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
98.71%
Matches word count
n/a
neededClean
false
words
194
94.06%
Dialogue to Total Word Ratio
Ratio: 94.97%, Deviation: 4.97%
neededClean
false
wordsTotal
199
wordsDialogue
189
96.3854%