NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ04WWQFWCJ1C8FY2SYRWAVQ
Run Details
Model:
Z.AI GLM 4.5 Air
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
4.3s
Cost:
$0.000199
Provider:
SiliconFlow
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
99.05%
Dialogue to Total Word Ratio
(details)
49.5254%
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
“Okay, the layout is key,” Molly whispered, tracing a pattern on the table. “We go in the back, through the bouncy castle.” Bill snorted. “The bouncy castle? Molly, it’s a death trap. A five-year-old in a Spider-Man costume could take us out in there.” “Fine,” she sighed. “Then we’re going through the ball pit. It’s our best cover.” “I am not wading through a hundred germ-infested plastic balls,” Bill hissed. “My dignity is worth more than whatever plastic junk is in those presents.” “It’s a Frozen II themed scooter, Bill. A Frozen II scooter. Think of the resale value.” He paced. “The real risk is the entertainment. We can’t have a rogue balloon animal artist foiling the entire operation.” “He’s just a guy with a poodle nose,” Molly argued. “We take him out with a well-aimed cheese cube.” Bill stopped pacing. “You’re a genius. Now, about the getaway… is the Mini-Van of Doom ready?”
created_at
"2026-04-24T16:24:19.964Z"
4/24/2026, 4:24:19 PM
model
"z-ai/glm-4.5-air"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1079
moderation_latency
(null)
generation_time
3135
tokens_prompt
77
tokens_completion
260
native_tokens_prompt
70
native_tokens_completion
220
native_tokens_completion_images
(null)
native_tokens_reasoning
0
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"
usage
0.000199
router
(null)
provider_responses
0
endpoint_id
"f7dc79ca-bbbd-41a1-8eef-616d981ff1cb"
id
"019dc04e762280ed677eece0910f8c66"
is_byok
false
latency
1076
model_permaslug
"z-ai/glm-4.5-air"
provider_name
"SiliconFlow"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777047859-bDjGW9RTt9ONACT2ZSwz"
session_id
(null)
api_type
"completions"
id
"gen-1777047859-OQ68bjyVBiCHlso7VQeC"
upstream_id
"019dc04e762280ed677eece0910f8c66"
total_cost
0.000199
cache_discount
(null)
upstream_inference_cost
0
provider_name
"SiliconFlow"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
154
99.05%
Dialogue to Total Word Ratio
Ratio: 86.88%, Deviation: 3.13%
neededClean
false
wordsTotal
160
wordsDialogue
139
49.5254%