NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-06-24-01KVX2MJZ4ZJTBWCDV60R7VYDQ
Run Details
Model:
Z.AI GLM 5.2 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
10.5s
Cost:
$0.001444
Provider:
Z.AI
Evaluation summary
Score
Evaluator
Details Link
86.38%
Matches word count
(details)
94.98%
Dialogue to Total Word Ratio
(details)
90.6791%
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 bush, yanking Bill down beside her. "You're telling me the target is a six-year-old's birthday party?" "Relax. Kids are distracted. Parents are drunk by noon. We walk in, grab the loot, walk out." "These are presents, Bill. Wrapped presents. We don't even know what's inside." "That's the beauty. It's a surprise for us too." "What if we steal a bunch of socks?" "Then we steal socks, Molly. I don't understand the problem." "The problem is I didn't spend three months in a safe house in Reno to boost gift cards and Polly Pockets." "It's Polly Pocket. Singular. And look, the cake alone is worth something. That thing has four tiers. Four." "That's not cake. That's a Costco sheet cake with a plastic Elsa jammed into it." "Works for me. I eat the cake, you bag the presents, we meet at the car in six minutes." "Fine. But I'm keeping whatever's in the biggest box." "Deal. I call dibs on the goody bags." "Nobody wants the goody bags, Bill." "I do. I collect tiny erasers." "You're a nightmare." "I'm an entrepreneur. Put on your party hat."
created_at
"2026-06-24T15:05:36.499Z"
6/24/2026, 3:05:36 PM
model
"z-ai/glm-5.2-20260616"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3627
moderation_latency
(null)
generation_time
10294
tokens_prompt
77
tokens_completion
338
native_tokens_prompt
73
native_tokens_completion
305
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
0.0014442
router
(null)
provider_responses
0
endpoint_id
"442ea97f-ad5e-40d5-b9a6-66e9e0417dce"
id
"20260624230537c438bea684c74e8f"
is_byok
false
latency
3627
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-1782313536-Qtn2LdKHXprvHYZ52EE4"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1782313536-hIZBvmyLY13kVHOt5iJI"
upstream_id
"20260624230537c438bea684c74e8f"
total_cost
0.0014442
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
86.38%
Matches word count
n/a
neededClean
false
words
189
94.98%
Dialogue to Total Word Ratio
Ratio: 94.76%, Deviation: 4.76%
neededClean
false
wordsTotal
191
wordsDialogue
181
90.6791%