NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-06-24-01KVX2S8TY37T4XWW8J623XDD9
Run Details
Model:
Z.AI GLM 5.2 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
10.4s
Cost:
$0.001501
Provider:
Z.AI
Evaluation summary
Score
Evaluator
Details Link
95.99%
Matches word count
(details)
90.16%
Dialogue to Total Word Ratio
(details)
93.0736%
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
"So here's the plan," Molly whispered, spreading the birthday invitation across the dashboard. "We go in through the back garden, blend with the parents, and start loading presents into the van." "Which one's the van?" "The one we stole yesterday." "Right. And what if someone asks who we are?" "We're Jenny's aunt and uncle from Manchester." "Which Jenny?" "The birthday girl, Bill. Try to keep up." "What if she has actual aunt and uncle from Manchester there?" "Then we improvise. Maybe we're the entertainers." "You can't juggle." "I can pretend to juggle. That's almost the same thing. Besides, nobody watches the entertainer at a kids' party. They're too busy fishing pizza out of their handbags and wondering when it's acceptable to leave." "And the presents?" "Grab the biggest ones first. Nothing with wrapping paper that rattles. That's usually board games. Board games are heavy and worth nothing on the black market." "There's a black market for children's presents?" "There's a black market for everything. I once sold a stolen trampoline to a vicar." "You're making that up." "I never make things up, Bill. Now put on your smile and help me carry this cake." "What cake?" "The distraction cake, Bill. Honestly, do I have to think of everything?"
created_at
"2026-06-24T15:08:09.965Z"
6/24/2026, 3:08:09 PM
model
"z-ai/glm-5.2-20260616"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
4311
moderation_latency
(null)
generation_time
9997
tokens_prompt
77
tokens_completion
389
native_tokens_prompt
73
native_tokens_completion
318
native_tokens_completion_images
(null)
native_tokens_reasoning
37
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
0.0015014
router
(null)
provider_responses
0
endpoint_id
"442ea97f-ad5e-40d5-b9a6-66e9e0417dce"
id
"20260624230810fd852b6a91be431e"
is_byok
false
latency
4311
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-1782313689-pn5Lt1oY15QQqWVmjcEn"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1782313689-qfNGMf0cvCM6zo3Ckdg1"
upstream_id
"20260624230810fd852b6a91be431e"
total_cost
0.0015014
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
95.99%
Matches word count
n/a
neededClean
false
words
208
90.16%
Dialogue to Total Word Ratio
Ratio: 95.67%, Deviation: 5.67%
neededClean
false
wordsTotal
208
wordsDialogue
199
93.0736%