NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-15-01KKS2S39NBQEX1PCVJA3ZM2KD
Run Details
Model:
Z.AI GLM 5 Turbo
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
7.0s
Cost:
$0.001100
Provider:
Z.AI
Evaluation summary
Score
Evaluator
Details Link
81.27%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
59.0303%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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, I'm not wearing the clown nose." "Bill, you're six foot four and built like a refrigerator. You need a disguise." "A beard isn't a disguise?" "You look like you're selling stolen TVs out of your van. Which, to be fair—" "Fine. Give me the nose." "And the wig." "Oh come on." "Curly red. It completes the illusion." "I look like Carrot Top's depressed cousin." "Perfect. Now, the target is a seven-year-old's birthday party. Backyard, bounce house, approximately twenty presents on the gift table near the fence." "Twenty presents. What's the haul look like?" "LEGO sets, a gaming console, some kind of electric scooter." "Scooter's gotta be worth three hundred alone." "Focus, Bill. I create a distraction by releasing the piñata early. While every kid storms the candy, you grab the presents and toss them over the fence to me." "What's my distraction?" "You're a clown. Make balloon animals or something." "I don't know how to make balloon animals." "Just squeak the balloons and look sad. Kids will leave you alone." "That's actually genius." "I know. Now put on the wig, Bozo. We got a party to crash."
created_at
"2026-03-15T15:45:31.964Z"
3/15/2026, 3:45:31 PM
model
"z-ai/glm-5-turbo-20260315"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2052
moderation_latency
(null)
generation_time
6953
tokens_prompt
77
tokens_completion
377
native_tokens_prompt
66
native_tokens_completion
324
native_tokens_completion_images
(null)
native_tokens_reasoning
63
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
0.00110016
router
(null)
provider_responses
0
endpoint_id
"9ce3b132-3a17-4fea-8092-0e8e519ed32b"
id
"20260315234532473c023633a24122"
is_byok
false
latency
2051
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-1773589531-GZt5uIuL25AyxZmVUJLX"
upstream_id
"20260315234532473c023633a24122"
total_cost
0.00110016
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Z.AI"
Evaluation details
Result
Evaluator
Details
Meta Data
81.27%
Matches word count
n/a
neededClean
false
words
188
36.79%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
190
wordsDialogue
190
59.0303%