NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-06-24-01KVX2SPRSBGW5BRXTJ2HBT7QT
Run Details
Model:
Z.AI GLM 5.2 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
9.9s
Cost:
$0.001616
Provider:
Z.AI
Evaluation summary
Score
Evaluator
Details Link
51.93%
Matches word count
(details)
99.75%
Dialogue to Total Word Ratio
(details)
75.8376%
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, staring at the bounce house through binoculars. "We go in as clowns." "Absolutely not." "Bill, nobody questions clowns at a kids party." "Nobody questions clowns because everyone's terrified of them. That's the opposite of blending in." "Fine. Pony operators." "There's already a pony operator. You want to start a turf war at a six-year-old's birthday?" Molly lowered the binoculars. "Since when do you care about operational realism? You once tried to rob a bank dressed as a pizza delivery guy." "That worked." "They called the actual pizza place, Bill. We got intercepted by a delivery driver named Tony who thought you were stealing his route." "That's ancient history. What's Plan C?" "We dress as parents." "Which parents?" "The kind that hover. The kind that ask about gluten-free cake. The kind that nobody remembers because they were too busy talking about nut allergies." Bill scratched his chin. "That's actually brilliant." "Obviously." "And once we're inside?" "Grab the gift table, walk out, load the van, drive. Thirty seconds, in and out." "What about the piñata?" "What about it?" "That thing's got to be full of candy, Molly. That's secondary income." "We are not stealing a piñata." "We're stealing from children, but the piñata is where you draw the line?" "Grab the piñata."
created_at
"2026-06-24T15:08:24.241Z"
6/24/2026, 3:08:24 PM
model
"z-ai/glm-5.2-20260616"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2828
moderation_latency
(null)
generation_time
9732
tokens_prompt
77
tokens_completion
419
native_tokens_prompt
73
native_tokens_completion
344
native_tokens_completion_images
(null)
native_tokens_reasoning
38
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
0.0016158
router
(null)
provider_responses
0
endpoint_id
"442ea97f-ad5e-40d5-b9a6-66e9e0417dce"
id
"20260624230824b3d42df694694310"
is_byok
false
latency
2828
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-1782313704-w2RfLHl2ceVFxUlvTFWU"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1782313704-UdNrWZEIXM9EQAZ7tzOE"
upstream_id
"20260624230824b3d42df694694310"
total_cost
0.0016158
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
51.93%
Matches word count
n/a
neededClean
false
words
216
99.75%
Dialogue to Total Word Ratio
Ratio: 92.24%, Deviation: 2.24%
neededClean
false
wordsTotal
219
wordsDialogue
202
75.8376%