NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-15-01KKS3454G0RYWCVJZZ423PG7J
Run Details
Model:
Z.AI GLM 5 Turbo
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
53.0s
Cost:
$0.017726
Provider:
Z.AI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.9997%
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, sweating profusely in the July heat while studying the suburban backyard through binoculars. Beside her, Bill furiously sketched a map of the patio, his brow furrowed in deep concentration. The objective was heavily fortified. A barricade of folding chairs surrounded a mountainous pile of wrapped cardboard boxes, likely containing action figures and poorly constructed plastic toys. Guarding the perimeter were at least a dozen small children hopped up on refined sugar and pure chaos. This was a suicide mission, but the payout was legendary. Bill tapped his pencil against the clipboard, pointing to a structural weakness in the defense line. "Target acquired. We hit the bouncy castle exactly at noon. Grab the gifts, and ditch the crying clown, Bill, very fast," Molly nodded, evaluating the escape route. A golden retriever sleeping near the fence posed a significant risk, but a distracted toddler with a juice box could easily serve as an adequate decoy. The sheer audacity of stealing every single present from the birthday party of a child was not lost on her. It was the ultimate score. They had trained for this exact scenario, enduring weeks of intensive playground surveillance. Nothing could stop them.
created_at
"2026-03-15T15:51:34.296Z"
3/15/2026, 3:51:34 PM
model
"z-ai/glm-5-turbo-20260315"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2003
moderation_latency
(null)
generation_time
52934
tokens_prompt
77
tokens_completion
5013
native_tokens_prompt
66
native_tokens_completion
5535
native_tokens_completion_images
(null)
native_tokens_reasoning
4701
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
0.017726208
router
(null)
provider_responses
0
endpoint_id
"9ce3b132-3a17-4fea-8092-0e8e519ed32b"
id
"202603152351340dc9542badbd4cc0"
is_byok
false
latency
2003
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-1773589894-HJEO69K6UHvuOutaPg9Q"
upstream_id
"202603152351340dc9542badbd4cc0"
total_cost
0.017726208
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: 10.50%, Deviation: 0.50%
neededClean
false
wordsTotal
200
wordsDialogue
21
99.9997%