NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-02-01M1GT65KYGP3C532T18WJ8JZ9
Run Details
Model:
Z.AI GLM 5.3 (Reasoning, Max)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
2m 24s
Cost:
$0.024786
Provider:
Z.AI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.9995%
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 crouched behind a bounce house shaped like a castle, binoculars pressed to her face despite the party being twelve feet away. "Guards?" whispered Bill. "Two clowns. Armed with balloons." Bill nodded gravely, as though balloon animals were improvised explosive devices. He unrolled a backyard schematic drawn in crayon, for authenticity. A lipstick X marked the present table between a piñata and a dinosaur cake. The plan was elegant. Molly would pose as entertainment, having borrowed a tutu and a severe misunderstanding of what magicians actually do. Bill would trigger the sprinklers, sending seven six-year-olds into a shrieking frenzy and their parents scrambling toward the tacos. "Twelve feet, Bill. Twelve," Molly muttered, lowering the binoculars. "The tutu is tactical," he replied, wounded. Molly had rehearsed for weeks. She could now saw a stuffed rabbit in half with total commitment. The score was substantial: forty presents, three gift cards, and a build-your-own-robot kit that Bill insisted was "for the fence, obviously." The birthday girl opened her first present. Zero hour. "On three," Molly breathed. They lunged—directly into the piñata. Bill went down hard, tangled in papier-mâché and disappointment, while Molly somersaulted onto the dinosaur cake. Somewhere, a clown honked.
created_at
"2026-09-02T10:21:13.221Z"
9/2/2026, 10:21:13 AM
model
"z-ai/glm-5.3-20260816"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
4308
moderation_latency
(null)
generation_time
143747
tokens_prompt
75
tokens_completion
5151
native_tokens_prompt
73
native_tokens_completion
5610
native_tokens_completion_images
(null)
native_tokens_reasoning
5322
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
0.0247862
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788344473-1op0fpTvUg4I9vrdOwfY"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788344473-rCq6J5m9Qe5WyOYIjKB5"
upstream_id
"20260902182113cb7cedf0101f4e95"
provider_responses
0
endpoint_id
"db975786-e7f6-4838-9e56-3e0b77f1bdc2"
id
"20260902182113cb7cedf0101f4e95"
is_byok
false
latency
4308
model_permaslug
"z-ai/glm-5.3-20260816"
provider_name
"Z.AI"
status
200
total_cost
0.0247862
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
199
100.00%
Dialogue to Total Word Ratio
Ratio: 9.76%, Deviation: 0.24%
neededClean
false
wordsTotal
205
wordsDialogue
20
99.9995%