NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-15-01KKS2S4CSA32YG1BPVMH9K45P
Run Details
Model:
Z.AI GLM 5 Turbo
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
1m 19s
Cost:
$0.035947
Provider:
Z.AI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
100.0000%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 unrolled the schematic across the greasy diner table, using a chicken nugget as a paperweight. Bill stared at the crude crayon drawing of suburban backyard defenses, his expression hollow. The Operation Ransom the Rainbow was their most daring job yet, targeting a local spoiled neighborhood birthday extravaganza. The payload was staggering: forty wrapped packages, ranging from plastic building blocks to what intelligence suggested was a lucrative robotic hamster cache. The security was laughably inept, consisting entirely of exhausted parents and a hired clown who looked one balloon animal away from a complete nervous breakdown. Getting past the obstacle course of spilled juice boxes would require absolute stealth. Molly tapped her finger against the inflatable fortress, outlining their extraction route. Bill nodded slowly, adjusting his ski mask in the middle of the July afternoon. He hated summer heists. The humidity ruined the adhesive on his fake mustache. Still, a thief had to eat, and those presents were practically begging to be liberated away from their capitalist confines. He checked his wristwatch, verifying the exact tactical timeline. Molly said, "We breach the bouncy castle at exactly noon today." Bill said, "Grab the huge Barbie dreamhouse and just run from the toddlers."
created_at
"2026-03-15T15:45:33.088Z"
3/15/2026, 3:45:33 PM
model
"z-ai/glm-5-turbo-20260315"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1334
moderation_latency
(null)
generation_time
78667
tokens_prompt
77
tokens_completion
9844
native_tokens_prompt
66
native_tokens_completion
11229
native_tokens_completion_images
(null)
native_tokens_reasoning
10981
native_tokens_cached
64
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.035947008
router
(null)
provider_responses
0
endpoint_id
"9ce3b132-3a17-4fea-8092-0e8e519ed32b"
id
"2026031523453339208e9b306b4d0d"
is_byok
false
latency
1334
model_permaslug
"z-ai/glm-5-turbo-20260315"
provider_name
"Z.AI"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer
(null)
api_type
"completions"
id
"gen-1773589533-Kn5Es6UzX7Ubcm2t4wpd"
upstream_id
"2026031523453339208e9b306b4d0d"
total_cost
0.035947008
cache_discount
0.00006144
upstream_inference_cost
0
provider_name
"Z.AI"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
100.00%
Dialogue to Total Word Ratio
Ratio: 10.00%, Deviation: 0.00%
neededClean
false
wordsTotal
200
wordsDialogue
20
100.0000%