NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-02-01M1GQA7Q5FZQRRA853GMC51JE
Run Details
Model:
Z.AI GLM 5.3 (Reasoning, Max)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
47.3s
Cost:
$0.012911
Provider:
Z.AI
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
98.67%
Dialogue to Total Word Ratio
(details)
99.2950%
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
Bill peered through the binoculars. "There. Bouncy castle at three o'clock." "A bouncy castle? You said this was a fortress." "It's got a net." "It's a children's party, Bill." "Which is exactly what they'd expect us to think. Twelve kids, one clown, one piñata." "Why presents, anyway?" "Kids' presents are small and expensive. Gift cards. Cash in envelopes. Somebody's bringing a Nintendo." "How do you know?" "I did recon at the last one." Molly lowered her sunglasses. "You were the magician, weren't you?" "The rabbit was a plant. Entry point: the slide. Nobody watches the slide." "You can't fit down a slide." "I've been training. Yogurt, twice a week." "There's a gate." "Alarmed?" "It's a balloon, Bill." "A popped balloon could trigger—" "It's tied to the fence with string." "String is basically a laser grid." "Or I walk in, say I'm the caterer, and carry the presents straight out." He lowered the binoculars. "That's not a heist. That's a Tuesday." "Fine. You take the slide, I'll take the door. Rendezvous at the piñata." "What if the clown makes us?" "Twist him a balloon dog and apologize." "To the dog or the clown?" "Just get the presents, Bill."
created_at
"2026-09-02T09:31:00.719Z"
9/2/2026, 9:31:00 AM
model
"z-ai/glm-5.3-20260816"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
4716
moderation_latency
(null)
generation_time
47241
tokens_prompt
75
tokens_completion
2638
native_tokens_prompt
73
native_tokens_completion
2911
native_tokens_completion_images
(null)
native_tokens_reasoning
2612
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
0.0129106
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788341460-iFL4pnsEHGjiEZSGkLQh"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788341460-6cqP8BSKkXmmWdZNc9gz"
upstream_id
"2026090217310011dc20c1cebf472f"
provider_responses
0
endpoint_id
"db975786-e7f6-4838-9e56-3e0b77f1bdc2"
id
"2026090217310011dc20c1cebf472f"
is_byok
false
latency
4716
model_permaslug
"z-ai/glm-5.3-20260816"
provider_name
"Z.AI"
status
200
total_cost
0.0129106
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
99.92%
Matches word count
n/a
neededClean
false
words
197
98.67%
Dialogue to Total Word Ratio
Ratio: 93.40%, Deviation: 3.40%
neededClean
false
wordsTotal
197
wordsDialogue
184
99.2950%