NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-06-24-01KVX30Q4GJVXDTC3TGFKAVQ78
Run Details
Model:
Z.AI GLM 5.2 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
46.3s
Cost:
$0.014090
Provider:
Z.AI
Evaluation summary
Score
Evaluator
Details Link
99.74%
Matches word count
(details)
99.96%
Dialogue to Total Word Ratio
(details)
99.8505%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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
"Are you really sure about this target, Molly? It is a bounce house, not a bank." Bill adjusted his black ski mask, sweating profusely under the heavy wool as loud pop music blared from the yard. "Think about the haul, Bill. It is a rich kid's birthday. We are talking massive Lego sets, iPads, and pure gift cards." Molly checked her tactical watch, carefully eyeing the chaotic throng of sugar-riddled first graders running amok on the soaking wet lawn. "What if they swarm us? Kids bite, Molly. They have no concept of proportional force." She pulled a canister of pepper spray from her utility belt, then hesitated and swapped it for a candy dart gun. "We go in as caterers. I will distract the birthday boy, you hit the present table. Grab all the shiny loot." Bill sighed, staring down at the oversized polka-dot chef hat he had been forced to wear during the final briefing. "If a six-year-old asks why we are taking the presents, what do I say?" Molly gave him a deadpan glare, carefully loading a bright pink gummy bear into the blowgun chamber. "Tell them the truth, Bill. Capitalism is a rigged game and we are merely the market correctors."
created_at
"2026-06-24T15:12:13.983Z"
6/24/2026, 3:12:13 PM
model
"z-ai/glm-5.2-20260616"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2506
moderation_latency
(null)
generation_time
46065
tokens_prompt
77
tokens_completion
3046
native_tokens_prompt
73
native_tokens_completion
3179
native_tokens_completion_images
(null)
native_tokens_reasoning
2912
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
0.0140898
router
(null)
provider_responses
0
endpoint_id
"442ea97f-ad5e-40d5-b9a6-66e9e0417dce"
id
"20260624231214765685beda534c0b"
is_byok
false
latency
2506
model_permaslug
"z-ai/glm-5.2-20260616"
provider_name
"Z.AI"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.16.0; linux; x64))"
http_referer
(null)
request_id
"req-1782313934-NFIMzaS07rQbImHuwK8Q"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1782313934-SQHtY0u159bIQ83qzcex"
upstream_id
"20260624231214765685beda534c0b"
total_cost
0.0140898
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Z.AI"
response_cache_source_id
(null)
data_region
"global"
Evaluation details
Result
Evaluator
Details
Meta Data
99.74%
Matches word count
n/a
neededClean
false
words
204
99.96%
Dialogue to Total Word Ratio
Ratio: 51.44%, Deviation: 1.44%
neededClean
false
wordsTotal
208
wordsDialogue
107
99.8505%