NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-15-01KKS39AG4T49HPZPA2E6J5QZ8
Run Details
Model:
Z.AI GLM 5 Turbo
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
1m 2s
Cost:
$0.021926
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 50% 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
Bill adjusted his black ski mask, sweat beading on his forehead. The suburban backyard was a highly volatile minefield of scattered plastic toys. He peeked through the wooden fence slats, spotting a massive mountain of brightly wrapped presents sitting completely unguarded near the picnic table. A terrifying giggle echoed from the bouncy castle nearby. Molly crouched beside him, carefully checking her watch before pulling a heavy crowbar from her jacket. She gestured toward the side gate with a sharp nod. They both took a deep breath, preparing to sprint across the grass. Tripping over a stray tricycle would mean death. "Are you sure about this crazy plan?" "Relax," "The piƱata is our diversion. Once it breaks, chaos erupts." "What about the clown guarding the patio?" "He is distracted by balloon animals. He is an amateur." "That is a lot of Barbie Dreamhouses down there." "High resale value on the black market," "We go in through the side gate, grab the loot, and bail before the cake cutting." "And what happens if a screaming kid catches us?" "We blame it entirely on the weird magician. Move out now." "I think we should have robbed a bank instead." "Shut up and run."
created_at
"2026-03-15T15:54:23.633Z"
3/15/2026, 3:54:23 PM
model
"z-ai/glm-5-turbo-20260315"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2062
moderation_latency
(null)
generation_time
61160
tokens_prompt
77
tokens_completion
5549
native_tokens_prompt
66
native_tokens_completion
6832
native_tokens_completion_images
(null)
native_tokens_reasoning
5251
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
0.02192576
router
(null)
provider_responses
0
endpoint_id
"9ce3b132-3a17-4fea-8092-0e8e519ed32b"
id
"20260315235424aaeb6e79a494445a"
is_byok
false
latency
2062
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-1773590063-Cv62pMXDKS6jDegbq0t2"
upstream_id
"20260315235424aaeb6e79a494445a"
total_cost
0.02192576
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: 50.00%, Deviation: 0.00%
neededClean
false
wordsTotal
200
wordsDialogue
100
100.0000%