NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-02-08-01KGYZXVTKJGZC5KFJY26J9MYP
Run Details
Model:
Z.AI GLM 4.6
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
1m 21s
Cost:
$0.004436
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
99.61%
Dialogue to Total Word Ratio
(details)
49.8051%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 tapped a greasy napkin, her expression grim. Their reconnaissance was complete. The target: a suburban backyard, the impenetrable fortress of a seven-year-old’s birthday party. The primary obstacle, according to her scribbled intel, was a man in a “Kiss the Cook” apron tending a grill. He was the heavy. Bill, meanwhile, was less concerned with the culinary sentry and more with the payload. He envisioned the extraction, a duffel bag filled with brightly wrapped boxes emitting cacophonous beeps and jingles. Stealth was impossible. “The weak point is the bouncy castle,” Molly hissed, pointing a grimy finger. Bill looked up from polishing a lockpick. “What about the squeakers?” “A calculated risk.” “I hate calculated risks.” Molly ignored his muttering, her finger tracing a path past a sleeping golden retriever—the silent alarm—and towards the prize table. She’d already disabled the piñata, a real grenade of potential noise, during her last dry run. For them, this was the big score. For everyone else, it was just Saturday.
created_at
"2026-02-08T16:05:24.722252+00:00"
2/8/2026, 4:05:24 PM
model
"z-ai/glm-4.6"
4/6/2001, 12:00:00 AM
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
236
moderation_latency
(null)
generation_time
80735
tokens_prompt
61
tokens_completion
2518
native_tokens_prompt
66
native_tokens_completion
2546
native_tokens_completion_images
(null)
native_tokens_reasoning
2421
native_tokens_cached
64
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
0.0044360199999552
router
(null)
provider_responses
0
id
"chatcmpl-RnSk6K7ig0DyqLIZIyGIXOGA"
status
200
is_byok
false
latency
62
endpoint_id
"c8607edc-8577-4199-b03d-1213da4743dc"
provider_name
"DeepInfra"
model_permaslug
"z-ai/glm-4.6"
4/6/2001, 12:00:00 AM
api_type
"completions"
id
"gen-1770566643-oR5hqSlNsopwKJbVOPBr"
upstream_id
"chatcmpl-RnSk6K7ig0DyqLIZIyGIXOGA"
total_cost
0.0044360199999552
cache_discount
0.0000224000000448
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
166
99.61%
Dialogue to Total Word Ratio
Ratio: 12.50%, Deviation: 2.50%
neededClean
false
wordsTotal
168
wordsDialogue
21
49.8051%