NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-02-01M1GS2BXT32SKEMXYH335KTET
Run Details
Model:
Z.AI GLM 5.3 (Reasoning, Max)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
10.1s
Cost:
$0.001528
Provider:
Z.AI
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
99.93%
Dialogue to Total Word Ratio
(details)
49.9659%
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 peered through the binoculars. "There's a bouncy castle, Bill. A bouncy castle." "So? We walk past it." "With dignity? You, in that clown costume?" "I'm a distraction, Molly. Clowns are beloved." "Clowns are terrifying. There's a difference." "Either way, people look away. That's the point." "And then what? There are thirty presents under that table." "Thirty-two. I counted the bows." "Of course you did. How do we carry them?" "The big sack. Santa sack. Very festive, very innocent." "You're a clown carrying a Santa sack." "It's a themed party, Molly." "It's a detective's dream is what it is. What's the exit strategy?" "Same as the entrance. Past the bouncy castle." "You're going to waddle through a bouncy castle with thirty-two presents?" "Twenty-eight. Some are socks." "You've done surveillance on the socks?" "A good thief knows his inventory." Bill adjusted his rubber nose. Molly sighed. "Fine. But if a child hugs you, you hug back. We're not monsters." "Obviously," said Bill. "I'm a professional."
created_at
"2026-09-02T10:01:40.034Z"
9/2/2026, 10:01:40 AM
model
"z-ai/glm-5.3-20260816"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2891
moderation_latency
(null)
generation_time
10049
tokens_prompt
75
tokens_completion
353
native_tokens_prompt
73
native_tokens_completion
324
native_tokens_completion_images
(null)
native_tokens_reasoning
73
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
0.0015278
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788343300-h4e7o7gqMsh05yo3rVvR"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788343300-1q3thQ453It4JzYLAYGZ"
upstream_id
"20260902180140865074bc6cab4775"
provider_responses
0
endpoint_id
"db975786-e7f6-4838-9e56-3e0b77f1bdc2"
id
"20260902180140865074bc6cab4775"
is_byok
false
latency
2891
model_permaslug
"z-ai/glm-5.3-20260816"
provider_name
"Z.AI"
status
200
total_cost
0.0015278
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
0.00%
Matches word count
n/a
neededClean
false
words
164
99.93%
Dialogue to Total Word Ratio
Ratio: 91.62%, Deviation: 1.62%
neededClean
false
wordsTotal
167
wordsDialogue
153
49.9659%