NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-02-08-01KGYZXK1CE79SX30MNSG0NGA6
Run Details
Model:
Z.AI GLM 4.7 Flash
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
1m 41s
Cost:
$0.001031
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
94.60%
Dialogue to Total Word Ratio
(details)
47.3023%
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
"The back door is glass, Molly. It’s too risky," Bill warned, tapping his temple. "Then we sneak past the parents," she retorted. "We pretend to be lost waiters. We ask for directions to the break room." "In a four-year-old's birthday party?" "Adults love incompetence. We offer free cotton candy. While their sugar high peaks, I’ll grab the gift bags and slip them into my pocket." "Who are we?" "We are the magicians. Jean-Claude and Pierre. We saw your wallet through the window, Monsieur. We will give it back if you hand over the loot." "This is extortion!" "It’s a heist! Focus! The clown is changing the balloons, that’s our window. Three seconds." "I’m ready." "Don't fart in the costume, Bill. You’ll ruin the illusion." "My waistband is airtight." "Good. On three. One, two..."
created_at
"2026-02-08T16:05:35.991384+00:00"
2/8/2026, 4:05:35 PM
model
"z-ai/glm-4.7-flash-20260119"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
184
moderation_latency
(null)
generation_time
100807
tokens_prompt
61
tokens_completion
2547
native_tokens_prompt
66
native_tokens_completion
2571
native_tokens_completion_images
(null)
native_tokens_reasoning
2466
native_tokens_cached
32
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
0.0010307600000064
router
(null)
provider_responses
0
id
"chatcmpl-Rg7TVZMFa77juzxc7gjaXopA"
status
200
is_byok
false
latency
54
endpoint_id
"6efb5994-8fcb-4300-9c64-ba393193f5f6"
provider_name
"DeepInfra"
model_permaslug
"z-ai/glm-4.7-flash-20260119"
api_type
"completions"
id
"gen-1770566634-aqLalkakxxPRAmhuVHjj"
upstream_id
"chatcmpl-Rg7TVZMFa77juzxc7gjaXopA"
total_cost
0.0010307600000064
cache_discount
0.0000015999999936
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
133
94.60%
Dialogue to Total Word Ratio
Ratio: 94.85%, Deviation: 4.85%
neededClean
false
wordsTotal
136
wordsDialogue
129
47.3023%