NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-02-01M1GQKMCJA3MS8CJKWGN0BQ4Y
Run Details
Model:
Z.AI GLM 5.3 (Reasoning, Max)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
2m 15s
Cost:
$0.041365
Provider:
Z.AI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
100.0000%
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 lowered her binoculars from behind the recycling bins, professionally. Across the street, eight six-year-olds were conducting basic training on a bouncy castle. "The perimeter is soft," she murmured. "No cameras. One clown." Bill consulted the dossier from three weeks of surveillance: a napkin with a smiley face on it. The target was little Tyler's backyard bash, presents estimated at thirty-two units, including one hoverboard, street value ninety dollars. His crew had cracked vaults in Geneva. This should be trivial. It was not trivial. The clown made balloon animals resembling nothing on God's green earth and had made eye contact with Bill twice. Somewhere, a piƱata swung like a pendulum, counting down their window. Cake at three, then presents, then screaming intense enough to scramble comms. Molly had planned for screaming. She had not planned for the mother circulating with juice boxes, offering them to strangers, warm and merciless. "We go in at nap-adjacent," she said. "Watch the clown. The clown sees everything." Bill nodded, sweating. He'd once held his breath four minutes in a Prague vault. He could survive one child's party. Probably. And then the clown waved at him. Bill flinched. Pure amateur hour. The clown knew it.
created_at
"2026-09-02T09:36:08.603Z"
9/2/2026, 9:36:08 AM
model
"z-ai/glm-5.3-20260816"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1229
moderation_latency
(null)
generation_time
135203
tokens_prompt
75
tokens_completion
8177
native_tokens_prompt
73
native_tokens_completion
9378
native_tokens_completion_images
(null)
native_tokens_reasoning
9106
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
0.0413654
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788341768-wkQSQpy9VKPXVyJUmL4G"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788341768-pJxTQRiTajaZ9XcZfrAh"
upstream_id
"2026090217360831a846c1d3954a0e"
provider_responses
0
endpoint_id
"db975786-e7f6-4838-9e56-3e0b77f1bdc2"
id
"2026090217360831a846c1d3954a0e"
is_byok
false
latency
1229
model_permaslug
"z-ai/glm-5.3-20260816"
provider_name
"Z.AI"
status
200
total_cost
0.0413654
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
100.00%
Matches word count
n/a
neededClean
false
words
200
100.00%
Dialogue to Total Word Ratio
Ratio: 10.29%, Deviation: 0.29%
neededClean
false
wordsTotal
204
wordsDialogue
21
100.0000%