NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-15-01KKS30ZCXDBKQR0BJ04EWETCF
Run Details
Model:
Z.AI GLM 5 Turbo
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
1m 3s
Cost:
$0.021705
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 adjusted her ski mask, impractical for a July afternoon but added necessary gravitas to the operation. She unrolled the blueprints across the sticky diner table, her eyes tracing the defense perimeter of the suburban backyard. A rogue ketchup packet threatened the structural integrity of the document, but she swatted it away with practiced precision. Bill, her partner in grand larceny and poor life choices, fiddled with a lockpicking kit that he had purchased at a dollar store. He smelled of desperation and cheap cologne. Stealing from an infant birthday party was a new low, but the sheer volume of unguarded Lego sets presented an irresistible payout. They were professionals, after all, and professionals did not discriminate based on the age of the victim. The plan was foolproof. "We hit the bouncy castle at noon," Molly whispered. "Good. The shiny wrapping paper is prime," Bill replied. "Grab the toys, leave the cake." Bill would create a diversion by releasing the family golden retriever, while Molly utilized a zip line to infiltrate the patio. Inside the party zone, they would neutralize the balloon arch, secure the loot, and vanish into the shadows before the clown even finished twisting his first poodle.
created_at
"2026-03-15T15:49:50.123Z"
3/15/2026, 3:49:50 PM
model
"z-ai/glm-5-turbo-20260315"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2146
moderation_latency
(null)
generation_time
62941
tokens_prompt
77
tokens_completion
5730
native_tokens_prompt
66
native_tokens_completion
6763
native_tokens_completion_images
(null)
native_tokens_reasoning
5416
native_tokens_cached
0
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
0.02170496
router
(null)
provider_responses
0
endpoint_id
"9ce3b132-3a17-4fea-8092-0e8e519ed32b"
id
"20260315234950408c2443f28a4eaa"
is_byok
false
latency
2146
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-1773589790-ouC7LXw8TbBvq8ugtxP2"
upstream_id
"20260315234950408c2443f28a4eaa"
total_cost
0.02170496
cache_discount
(null)
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%