NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-02-01M1GSJF5T87831W4PFYX33AGH
Run Details
Model:
Z.AI GLM 5.3 (Reasoning, Max)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
1m 30s
Cost:
$0.020927
Provider:
Z.AI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
98.99%
Dialogue to Total Word Ratio
(details)
99.4972%
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 lay flat in the Hendersons' hydrangeas, binoculars pressed to her face. Beyond the fence, a swarm of six-year-olds ricocheted around a bouncy castle like piranhas wearing party hats. "Two clowns, one bouncy castle, twelve targets, and a pony," she murmured. Bill crouched beside her, studying surveillance photos taped to a clipboard. His hands—steady enough to disarm a laser grid in Monte Carlo—trembled at the sight of a piñata dangling from the oak. "Presents are stacked behind the slide, under the balloons," he said. Three days of casing had yielded schedules, nap times, and the precise moment every small head would turn toward the cake. Bill had infiltrated yesterday as a balloon-animal assistant, returning traumatized but informed. The plan was elegant. During the birthday song, Molly would slip through the side gate while Bill created a diversion by unleashing the pony. Ninety seconds later, every gift would be in their van. Bill pulled on his gloves. Twenty years of professional theft, and he'd never been this nervous. Somewhere beyond that hedge, a child was about to lose a Build-A-Bear, and Bill would have to live with that. "Ready?" Molly asked. He nodded. Heists were simpler when nobody cried.
created_at
"2026-09-02T10:10:27.652Z"
9/2/2026, 10:10:27 AM
model
"z-ai/glm-5.3-20260816"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1623
moderation_latency
(null)
generation_time
89594
tokens_prompt
75
tokens_completion
4329
native_tokens_prompt
73
native_tokens_completion
4733
native_tokens_completion_images
(null)
native_tokens_reasoning
4456
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
0.0209274
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788343827-V7KqR90p2PWBFbYhUXV6"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788343827-kAucY5klDbDigmfasMCX"
upstream_id
"202609021810272f311cbe89b945ab"
provider_responses
0
endpoint_id
"db975786-e7f6-4838-9e56-3e0b77f1bdc2"
id
"202609021810272f311cbe89b945ab"
is_byok
false
latency
1623
model_permaslug
"z-ai/glm-5.3-20260816"
provider_name
"Z.AI"
status
200
total_cost
0.0209274
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
98.99%
Dialogue to Total Word Ratio
Ratio: 13.17%, Deviation: 3.17%
neededClean
false
wordsTotal
205
wordsDialogue
27
99.4972%