NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ04CS62QBYXGQ83MFP4W6WZ
Run Details
Model:
Z.AI GLM 5.1
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
8m 54s
Cost:
$0.077964
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
88.80%
Dialogue to Total Word Ratio
(details)
94.3983%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 500 word scene that has 70% 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 tapped the crinkled surveillance photo against the steering wheel of the idling van, her eyes narrowed at the sprawling suburban backyard. The target was a modest two-story colonial with an above-ground pool and a suspicious lack of security cameras. Bill sat slumped in the passenger seat, licking a blue raspberry lollipop he’d stolen from a stakeout three counties over. The old van smelled like stale coffee and desperation. "So, you got the layout?" "I got the Pinterest board. It’s a unicorn theme this year. Heavy on the pastel, light on the exits." "Unicorns? So the laser grid is pink?" "Look at the imagery. The presents are stacked by the piñata. Right under the patio awning." "Piñata. That’s our entry point." "The piñata is our entry point? It’s a paper mache donkey, Bill." "Exactly. Nobody guards a donkey. I climb the oak tree, swing down on a streamer rope, and cut it open." "The kids cut it open. With a bat. While blindfolded." "Which is why I’ll be wearing a blindfold! Camouflage." Molly sighed, rubbing her temples. The intel was bad, the perimeter was crawling with sugar-crazed toddlers, and her partner was an absolute moron. "We go through the bouncy castle." "I am not bouncing. I have a bad ankle." "You slice the side with a knife, roll in, grab the loot, and roll out. Tactical infiltration of an inflatable structure." Bill shifted uncomfortably, his knee bumping the glove box. He stared out the window, visualizing the tactical challenges of vinyl warfare. "What about the clown?" "What about him? He's just a guy in makeup." "He’s armed. I saw him making balloon animals. Packing twistable latex. Probably has a squirt flower too." "He’s a clown. You take him out first." "Take him out? I’m not hitting a clown! I have standards." "I mean distract him! Give him a twenty and tell him there’s a better party down the street." "Clowns are territorial. They mark their territory with honks." "Fine. I’ll handle the clown. You handle the presents." "What kind of presents? If it’s Dollar Store slime, I’m out. I can't fence slime." "It’s a seven-year-old’s in the Heights. Legos, American Girl dolls, Nintendo Switches. High yield, low weight." "Okay. I’m in. But what if the kids see us?" "They’re hopped up on frosting. We throw glitter and release a stray puppy. They scatter like roaches." "We don’t have a puppy, Molly." "I’ll borrow one from the pound. Extraction is over the fence with the swag bags, into the van, and on the interstate before he blows out the candles." "What if the birthday boy makes a wish?" "He’ll wish for a pony. He’s getting a life lesson instead." Bill reached into the backseat for his gear, pulling a black balaclava over his head. He adjusted the eye holes and checked his reflection, frowning at the fit. "I was thinking we wear face paint. Blend in with the clown." "Absolutely not. No face paint, no bunny ears. Standard tactical black. Let’s move."
created_at
"2026-04-24T16:15:32.043Z"
4/24/2026, 4:15:32 PM
model
"z-ai/glm-5.1-20260406"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2568
moderation_latency
(null)
generation_time
534178
tokens_prompt
77
tokens_completion
21162
native_tokens_prompt
66
native_tokens_completion
22271
native_tokens_completion_images
(null)
native_tokens_reasoning
20355
native_tokens_cached
64
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
0.07796372
router
(null)
provider_responses
0
endpoint_id
"e888c44c-6a07-4a9e-bc56-cb26511865ec"
id
"chatcmpl-RsrjHCZt8xwBLDEBVlrTkj0Y"
is_byok
false
latency
101
model_permaslug
"z-ai/glm-5.1-20260406"
provider_name
"DeepInfra"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777047332-okJga4IXKLvHZsv1kmdV"
session_id
(null)
api_type
"completions"
id
"gen-1777047332-IvvUJAP3TmjtvBpHn12V"
upstream_id
"chatcmpl-RsrjHCZt8xwBLDEBVlrTkj0Y"
total_cost
0.07796372
cache_discount
0.000054079
upstream_inference_cost
0
provider_name
"DeepInfra"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
501
88.80%
Dialogue to Total Word Ratio
Ratio: 71.54%, Deviation: 1.54%
neededClean
false
wordsTotal
506
wordsDialogue
362
94.3983%