NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-02-08-01KGYYAT5Q3VH5CRFDA06SPZV6
Run Details
Model:
Z.AI GLM 4.7
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
50.8s
Cost:
$0.002115
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
18.3940%
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
"Intel suggests the target is a piñata shaped like a unicorn." "Unicorns don't exist, Bill. Neither does the profit margin here." "It’s not about the cash, it’s about the principle. That ungrateful brat doesn't deserve a bicycle." "So we’re stealing a bicycle to teach a stranger’s kid a lesson?" "We’re liberating high-end electronics. I saw an iPad box under the banner." "That was a lunchbox, you idiot." "Plan B: I create a diversion by tripping the hired entertainer. You sweep the pile." "You want me to tackle a guy in a SpongeBob costume?" "He’s the only armed guard. Take him out, Molly. For the team." "I hate this job. What if the parents call the cops?" "Who arrests two grown adults stealing wrapping paper? They’ll just think we’re pathetic." "We *are* pathetic." "Exactly. Pathetic people get mercy sentences. Move in five."
created_at
"2026-02-08T15:37:02.47709+00:00"
2/8/2026, 3:37:02 PM
model
"z-ai/glm-4.7-20251222"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
275
moderation_latency
(null)
generation_time
50756
tokens_prompt
61
tokens_completion
1200
native_tokens_prompt
66
native_tokens_completion
1205
native_tokens_completion_images
(null)
native_tokens_reasoning
1058
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
0.00211467
router
(null)
provider_responses
0
id
"chatcmpl-RB6JYSOaXgxbVfRmuJhBpoEs"
status
200
is_byok
false
latency
56
endpoint_id
"ab79ffa8-8dcc-41c4-9a9f-6cc408135243"
provider_name
"DeepInfra"
model_permaslug
"z-ai/glm-4.7-20251222"
api_type
"completions"
id
"gen-1770564970-U6sUc0LVqgIgsCvR2hE0"
upstream_id
"chatcmpl-RB6JYSOaXgxbVfRmuJhBpoEs"
total_cost
0.00211467
cache_discount
0.00002048
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
141
36.79%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
142
wordsDialogue
142
18.3940%