NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-02-01M1GTBTZERHWVVS6EGGSR9C7E
Run Details
Model:
Z.AI GLM 5.3 (Reasoning, Max)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
1m 2s
Cost:
$0.018509
Provider:
Z.AI
Evaluation summary
Score
Evaluator
Details Link
75.16%
Matches word count
(details)
99.94%
Dialogue to Total Word Ratio
(details)
87.5490%
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 and Bill crouched behind a bouncy castle. "Target's inside the house. Parents moved the presents at 1400 hours," Bill whispered. "Bill, it's a birthday party, not Fort Knox." "Vigilance, Molly. What's our entry point?" "The front door. Someone will ask us to carry the cake." "We go in through the window. I've got the glass cutter." "You'll terrify the children." "I'll be wearing the clown suit." "The clown suit is terrifying." "It's tactical camouflage! Clowns are invisible at children's parties." "Clowns are why children need therapy, Bill." "Fine. I'm the balloon animal guy. Kids love balloon animals." "Can you make balloon animals?" "I can make a snake. It's a long balloon." "You'll blow our cover in four seconds." Bill consulted a napkin covered in crayon diagrams. "Recon complete. Seven kids, one piñata, mom on wine. The piñata's the real threat." "The piñata?" "It's a dragon full of candy. The kids get bats. When it breaks, stampede. That's our window." "You've planned an escape route around a piñata." "Through the hedge, past the sprinkler, into the getaway van." "You drove your mom's minivan again?" "It's gray. Gray is stealth." "Gray is beige's sad cousin. Fine. But we're leaving the birthday girl's present." "Sentimental?" "Practical. It's a karaoke machine. That thing's a security system."
created_at
"2026-09-02T10:24:18.936Z"
9/2/2026, 10:24:18 AM
model
"z-ai/glm-5.3-20260816"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2170
moderation_latency
(null)
generation_time
62140
tokens_prompt
75
tokens_completion
3628
native_tokens_prompt
73
native_tokens_completion
4200
native_tokens_completion_images
(null)
native_tokens_reasoning
3868
native_tokens_cached
64
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
0.01850924
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788344658-GoMymjs69vUkGDU8JjoF"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788344658-NhB4sp0swKttLogpu2wz"
upstream_id
"20260902182419947997083fd84941"
provider_responses
0
endpoint_id
"db975786-e7f6-4838-9e56-3e0b77f1bdc2"
id
"20260902182419947997083fd84941"
is_byok
false
latency
2170
model_permaslug
"z-ai/glm-5.3-20260816"
provider_name
"Z.AI"
status
200
total_cost
0.01850924
cache_discount
0.00007296
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
75.16%
Matches word count
n/a
neededClean
false
words
213
99.94%
Dialogue to Total Word Ratio
Ratio: 91.55%, Deviation: 1.55%
neededClean
false
wordsTotal
213
wordsDialogue
195
87.5490%