NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-02-01M1GT0ED4ZN78V0NQG06MXY17
Run Details
Model:
Z.AI GLM 5.3 (Reasoning, Max)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
2m 58s
Cost:
$0.025980
Provider:
Z.AI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
87.69%
Dialogue to Total Word Ratio
(details)
93.8460%
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 spread the plans across the kitchen table. "Bill, the vents are out. It's a bouncy castle." "So we bounce in." "You're two hundred pounds. It's not load-bearing." "Fine. Clown entrance. I do balloons." "You did balloons once, in prison, badly." "Skill transfer, Molly." "And your clown name?" "Bonko." "Bonko's doing five to ten for tax fraud. We've been over this." "Sprinkles, then. Now, once inside, I locate the present table." "It's in the kitchen, under a banner reading HAPPY BIRTHDAY, TYLER." "Which kitchen?" "There's one kitchen, Bill. It's a semi-detached house, not a casino." "Okay. Timing?" "We hit during Happy Birthday. Candles out, lights off, everyone blind." "Blinded by candles?" "Cake blindness, Bill. Documented phenomenon." "Estimated haul?" "Twenty presents, give or take." "Plus cake." "We're stealing cake now?" "Clowns need energy, Molly." "And my job?" "Getaway. Van gassed up?" "It's your mother's Corsa. And no." "Plan B. Tricycle." "Whose tricycle?" "Sourced one this morning." "You stole a tricycle to steal presents from children?" "Requisitioned. From Tyler." "Bill, Tyler is the birthday boy." "Exactly. Maximum emotional cover. Nobody suspects a crying clown." "Sprinkles doesn't cry, Bill. Sprinkles serves hard time." "Then he weeps on the inside. Like a professional."
created_at
"2026-09-02T10:18:05.616Z"
9/2/2026, 10:18:05 AM
model
"z-ai/glm-5.3-20260816"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1389
moderation_latency
(null)
generation_time
178360
tokens_prompt
75
tokens_completion
5239
native_tokens_prompt
73
native_tokens_completion
5898
native_tokens_completion_images
(null)
native_tokens_reasoning
5560
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
0.02598044
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788344285-N4rTtGQTihmtLVmIg3oV"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788344285-aAJaXWevSOPh7XxrUkw2"
upstream_id
"20260902181806d7de167af1c44003"
provider_responses
0
endpoint_id
"db975786-e7f6-4838-9e56-3e0b77f1bdc2"
id
"20260902181806d7de167af1c44003"
is_byok
false
latency
1389
model_permaslug
"z-ai/glm-5.3-20260816"
provider_name
"Z.AI"
status
200
total_cost
0.02598044
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
100.00%
Matches word count
n/a
neededClean
false
words
199
87.69%
Dialogue to Total Word Ratio
Ratio: 96.02%, Deviation: 6.02%
neededClean
false
wordsTotal
201
wordsDialogue
193
93.8460%