NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-02-01M1GWZ0AJQSFGTN8AWR0PMX36
Run Details
Model:
Z.AI GLM 5.3 (Reasoning, Max)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
2m 13s
Cost:
$0.030147
Provider:
Z.AI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
91.26%
Dialogue to Total Word Ratio
(details)
95.6278%
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 crouched behind the hedge. "Okay, the cake comes out at three. That's our window." "Which one's the cake?" Bill whispered. "The singing, Bill. When they sing, we move." "How do you know all this?" "I surveilled. There was an Evite." "I don't know, Molls. Stealing kids' presents? Feels low." "It's a rich kid's party. He's getting a PS5." "He's seven!" "Exactly. He can't even spell PlayStation." Bill sighed. "Fine. What's my cover?" "You're the balloon guy." "I don't make balloon animals." "You twist and sweat. Kids love that." "What if they ask for a giraffe?" "Say it flew away. Grief, Bill. Show grief." "That's messed up." "It's showmanship. Meanwhile, I'm on cake duty." "Distracting the parents with what?" "With you sweating over a giraffe." "This is a bad plan." "It's our fourth bad plan this month. We're due." "The last one ended with you trapped in a ball pit." "Which is why I know the layout. That's called experience." "Fine. But if a kid hugs me, I'm out." "Nobody's hugging you, Bill." "Kids hug me. I have a huggable face." "Nobody said huggable." "Strangers have said it!" "You have a face, all right. Now get in there and twist."
created_at
"2026-09-02T11:09:44.298Z"
9/2/2026, 11:09:44 AM
model
"z-ai/glm-5.3-20260816"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
5990
moderation_latency
(null)
generation_time
132640
tokens_prompt
75
tokens_completion
5413
native_tokens_prompt
73
native_tokens_completion
6845
native_tokens_completion_images
(null)
native_tokens_reasoning
6533
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
0.03014724
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788347384-NW8Q6dgWACNwq6Mb7fGh"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788347384-d3rvAAs3M70udKSqQw0a"
upstream_id
"2026090219094450bc402e3ab44e7e"
provider_responses
0
endpoint_id
"db975786-e7f6-4838-9e56-3e0b77f1bdc2"
id
"2026090219094450bc402e3ab44e7e"
is_byok
false
latency
5990
model_permaslug
"z-ai/glm-5.3-20260816"
provider_name
"Z.AI"
status
200
total_cost
0.03014724
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
200
91.26%
Dialogue to Total Word Ratio
Ratio: 95.50%, Deviation: 5.50%
neededClean
false
wordsTotal
200
wordsDialogue
191
95.6278%