NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ03KQCKDAZFYN40T433YWTC
Run Details
Model:
Z.AI GLM 4.5 Air
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
29.6s
Cost:
$0.000498
Provider:
SiliconFlow
Evaluation summary
Score
Evaluator
Details Link
3.62%
Matches word count
(details)
91.38%
Dialogue to Total Word Ratio
(details)
47.4992%
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
"Right, presents. All of 'em. We hit the bouncy castle first, quick snatch and grab," Molly said, tracing a path on the dashboard. "Bill, you're on balloon duty. Create a diversion, make 'em look up." "Balloon duty? Molly, I look ridiculous in a big purple hat. Remember the garden gnome incident?" "It was a fetching hat. Focus. While they're watching the floating badger, I slip in through the petting zoo enclosure. The goats won't snitch." "Goats? Molly, those things eat everything! Including fingers! What if I get nibbled?" "The risk is part of the thrill, Bill. Or we could go with Plan B. You dress as the magician. 'Abracadabra! Presents vanish!'" "And my magnificent purple hat?" "Perfect. Now, the real question: do we go before or after the piñata? Post-piñata means less candy competition, pre-piñata means the kids are distracted by the stick. Decisions, decisions." "Can't we just ask nicely? They'd share, right?" "Molly, this is a heist! Not a playdate. Now, hand me the grappling hook. And the purple hat. You look fabulous in hats."
created_at
"2026-04-24T16:01:51.004Z"
4/24/2026, 4:01:51 PM
model
"z-ai/glm-4.5-air"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3597
moderation_latency
(null)
generation_time
29513
tokens_prompt
77
tokens_completion
648
native_tokens_prompt
66
native_tokens_completion
568
native_tokens_completion_images
(null)
native_tokens_reasoning
304
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
0.00049772
router
(null)
provider_responses
0
endpoint_id
"f7dc79ca-bbbd-41a1-8eef-616d981ff1cb"
id
"019dc039edb8c3ffca9e3fc9902bfac7"
is_byok
false
latency
3597
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-1777046511-62AKGRC8o7XxxS5lTWak"
session_id
(null)
api_type
"completions"
id
"gen-1777046511-da4BuTNG8v4Y5fWInpNj"
upstream_id
"019dc039edb8c3ffca9e3fc9902bfac7"
total_cost
0.00049772
cache_discount
(null)
upstream_inference_cost
0
provider_name
"SiliconFlow"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
3.62%
Matches word count
n/a
neededClean
false
words
176
91.38%
Dialogue to Total Word Ratio
Ratio: 95.48%, Deviation: 5.48%
neededClean
false
wordsTotal
177
wordsDialogue
169
47.4992%