NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-02-11-01KH7GWB9G1EG0ETA71KJGHYKA
Run Details
Model:
Z.AI GLM 5
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
41.0s
Cost:
$0.007845
Provider:
Novita
Evaluation summary
Score
Evaluator
Details Link
98.71%
Matches word count
(details)
66.80%
Dialogue to Total Word Ratio
(details)
82.7585%
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 want us to hit the Patterson place at high noon?" Bill asked. "It's a brunch party, Bill. Precision timing is key," Molly said. "It's a six-year-old's birthday. There will be sugar-high maniacs everywhere." "Which is exactly why we go in disguised as entertainment." "You bought a bouncy castle?" "I bought a bouncy castle suit. It’s inflatable, surprisingly agile, and offers ballistic protection against juice boxes." "What about the parents?" "Distracted by the clowns. Plus, I've got the thermal cutters for the wrapping paper." "Molly, last time you used thermal cutters, you set the neighbor’s cat on fire." "That cat was highly flammable. These ribbons are tactical grade." "My contact says the piñata is a decoy." "A decoy filled with what?" "Broccoli. It's a trap." "And the getaway?" "The slide, Bill. We exit via the slide. It leads directly to the sidewalk." "What if a kid follows us down the slide?" "You give them a balloon animal. A giraffe. Distract them with art." "I can't make a giraffe. I can make a snake." "Then make a very long snake and run! Just remember, grab the Legos first. Those things are currency on the street."
created_at
"2026-02-11T23:34:56.879987+00:00"
2/11/2026, 11:34:56 PM
model
"z-ai/glm-5-20260211"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
780
moderation_latency
(null)
generation_time
40896
tokens_prompt
77
tokens_completion
2504
native_tokens_prompt
66
native_tokens_completion
2431
native_tokens_completion_images
(null)
native_tokens_reasoning
2182
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
0.0078452
router
(null)
provider_responses
0
id
"4b194fb02c8c4a167f1f62db4a84d63f"
status
200
is_byok
false
latency
780
endpoint_id
"898a8e6d-04a4-48c0-8457-36690a68782b"
provider_name
"Novita"
model_permaslug
"z-ai/glm-5-20260211"
api_type
"completions"
id
"gen-1770852855-lTW7Khl9H8mQfA3Ht56T"
upstream_id
"4b194fb02c8c4a167f1f62db4a84d63f"
total_cost
0.0078452
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Novita"
Evaluation details
Result
Evaluator
Details
Meta Data
98.71%
Matches word count
n/a
neededClean
false
words
194
66.80%
Dialogue to Total Word Ratio
Ratio: 97.97%, Deviation: 7.97%
neededClean
false
wordsTotal
197
wordsDialogue
193
82.7585%