NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-06-24-01KVX2Y7ZGFF7T6QEPM91G5AHP
Run Details
Model:
Z.AI GLM 5.2 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
8.4s
Cost:
$0.001413
Provider:
Z.AI
Evaluation summary
Score
Evaluator
Details Link
43.38%
Matches word count
(details)
53.29%
Dialogue to Total Word Ratio
(details)
48.3340%
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. "We go in as clowns." "Clowns? I hate clowns. Clowns are creepy." "That's the point, Bill. Nobody questions a clown at a kid's party." "I don't even know how to make a balloon animal." "You don't need to make a balloon animal. You need to make a distraction while I stuff presents into this sack." "What kind of distraction?" "I don't know, fall down. Do something funny. You're a clown." "What if a kid asks me to juggle?" "Tell them you're on break." "Clowns don't take breaks, Molly. That's not a thing." "Then tell them your juggling balls got stolen by another clown. Now stop arguing and put on the nose." "Which nose?" "The red one. The big one." "It smells like rubber and sadness." "That's the smell of crime, Bill. Now get in there." "What if there's a bouncy castle?" "Then you bounce past it." "What if there's a magician?" "Then you out-magic him. I don't care. We're here for those presents." "Molly, there's like forty kids in there." "Exactly. Forty kids who can't catch us."
created_at
"2026-06-24T15:10:52.923Z"
6/24/2026, 3:10:52 PM
model
"z-ai/glm-5.2-20260616"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2932
moderation_latency
(null)
generation_time
8258
tokens_prompt
77
tokens_completion
335
native_tokens_prompt
73
native_tokens_completion
298
native_tokens_completion_images
(null)
native_tokens_reasoning
35
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
0.0014134
router
(null)
provider_responses
0
endpoint_id
"442ea97f-ad5e-40d5-b9a6-66e9e0417dce"
id
"20260624231053ffd56e95e2a64c78"
is_byok
false
latency
2932
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-1782313852-FpSs8M5QJmlHIdXDiNez"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1782313852-Oh2GMTWYIxrWNXBRJNUh"
upstream_id
"20260624231053ffd56e95e2a64c78"
total_cost
0.0014134
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
43.38%
Matches word count
n/a
neededClean
false
words
183
53.29%
Dialogue to Total Word Ratio
Ratio: 98.91%, Deviation: 8.91%
neededClean
false
wordsTotal
183
wordsDialogue
181
48.3340%