NC Bench
Overview
About
Tests
Models
Model
Z.AI GLM 4.7
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2026-02-08-01KGYX36BF1Q4VHP0R76V7R9Y3
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
"Target is locked. Bounce castle inflating, perimeter security is non-existent." "Relax, it’s a garden fence." "Never relax! We have a window of three minutes before the pony rides start." "The pony rides aren't security, Bill." "They are obstacles! The distraction team is late. We need that juice box diversion before the magician arrives." "You’re overthinking this. Walk in, smile at the parents, grab the pile, and walk out." "And get caught? We’re professionals. We need a tactical exit." "Through the back gate?" "No. We need a zip-line from the roof. We rappel down, snatch the gifts, and vanish into the suburban afternoon." "It’s 2 PM on a Tuesday. There is no vanishing." "Details! Look, there’s the loot. A six-foot stack of unboxed joy." "Focus, Bill. We’re here for the electronics, not the plushies." "I need that giant panda, Molly. It calls to me." "You can’t fence a teddy bear!" "I’m keeping it. Now, what’s the code word?" "Boogers?" "Too juvenile. We go with 'Napkin'." "I see movement. Is that a party clown?" "Tactical units. Move!" "Fine. Cover me. I’m going in." "God help us. Don't touch the cake!"
created_at
"2026-02-08T15:17:10.6936+00:00"
Sunday, February 8th, 2026 at 3:17:10 PM GMT+00:00
model
"z-ai/glm-4.7-20251222"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
741
moderation_latency
(null)
generation_time
157918
tokens_prompt
61
tokens_completion
3098
native_tokens_prompt
66
native_tokens_completion
3121
native_tokens_completion_images
(null)
native_tokens_reasoning
2932
native_tokens_cached
32
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
0.00547791
router
(null)
provider_responses
0
id
"chatcmpl-RWd2LMJn1glvpmK0sCcpIK2X"
status
200
is_byok
false
latency
58
endpoint_id
"ab79ffa8-8dcc-41c4-9a9f-6cc408135243"
provider_name
"DeepInfra"
model_permaslug
"z-ai/glm-4.7-20251222"
api_type
"completions"
id
"gen-1770563672-TiUI30dhlzC0Hh5VBz5S"
upstream_id
"chatcmpl-RWd2LMJn1glvpmK0sCcpIK2X"
total_cost
0.00547791
cache_discount
0.00001024
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
93.6496%
Matches word count
n/a
neededClean
false
words
191
36.7879%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
191
wordsDialogue
191
65.2188%