NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-06-24-01KVX2E58CHSDJ8ARXDH91S39Z
Run Details
Model:
Z.AI GLM 5.2 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
46.2s
Cost:
$0.010667
Provider:
Z.AI
Evaluation summary
Score
Evaluator
Details Link
98.71%
Matches word count
(details)
96.36%
Dialogue to Total Word Ratio
(details)
97.5368%
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 adjusted her binoculars. Bill chewed a cold slice of pizza. "Bill, this is a masterpiece of a heist plan." "Molly, it's a child's birthday party." "Exactly. Low security, high yield." "It's a six-year-old's party. The yield is mostly Legos and plastic dinosaurs." "And iPads, Bill. Rich parents always bring iPads to keep the brats quiet. Plus, we go in disguised as clowns." "I am absolutely not wearing the red nose." "You have to wear the red nose. It's essential operational camouflage." "It pinches my septum and makes me sneeze glitter." "Do you want the presents or not?" "I want to not get tackled by an angry father in cargo shorts." "We go in, we make a quick balloon poodle, we pack the loot into our giant oversized shoes, and we walk out undetected." "What if a little kid asks for a giraffe?" "You make a giraffe, Bill. Just improvise." "I don't know how to make a giraffe! I went to theft school, not clown college. This is a total disaster." "Then just make a long green snake and call it a giraffe with a severe neck ache. They're six. They don't know zoology."
created_at
"2026-06-24T15:02:05.849Z"
6/24/2026, 3:02:05 PM
model
"z-ai/glm-5.2-20260616"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3407
moderation_latency
(null)
generation_time
46118
tokens_prompt
77
tokens_completion
2295
native_tokens_prompt
73
native_tokens_completion
2401
native_tokens_completion_images
(null)
native_tokens_reasoning
2132
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
0.0106666
router
(null)
provider_responses
0
endpoint_id
"442ea97f-ad5e-40d5-b9a6-66e9e0417dce"
id
"20260624230206a13531672ab34953"
is_byok
false
latency
3407
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-1782313325-mSuQhQIIKjd6VpJS4ScW"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1782313325-YEBRRP5MDUG0zu5lruU3"
upstream_id
"20260624230206a13531672ab34953"
total_cost
0.0106666
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
98.71%
Matches word count
n/a
neededClean
false
words
194
96.36%
Dialogue to Total Word Ratio
Ratio: 94.39%, Deviation: 4.39%
neededClean
false
wordsTotal
196
wordsDialogue
185
97.5368%