NC Bench
Overview
About
Tests
Models
Model
Z.AI GLM 4.7
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2026-02-08-01KGYZS0BNEAP422MYXW453E89
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
"So, the target is a six-year-old’s birthday bash? You’re serious right now?" "Deadly serious. We hit the bouncy castle at fourteen hundred hours sharp." "The bouncy castle? That’s our tactical insertion point?" "It’s the only blind spot. The parents are too busy arguing over cheap rosé to notice a tactical extraction from the ball pit." "What about the perimeter security?" "Golden Retriever named Buster. Loves peanut butter. I've got the distraction kibble right here." "And the loot?" "Wrapped boxes, mostly LEGOs and unrecognizable dolls. High resale value on the black market for desperate parents who forgot birthdays." "This is insane. We’re robbing a kid named Timmy." "We’re liberating assets. Look, are you in or are you going back to stealing copper wire from construction sites?" "I'm in. But if I see a clown, I'm bailing. I have a legitimate phobia." "Deal. Pass me the grappling hook. We need to scale the fence before the cake cutting ceremony starts." "You know, this isn't exactly Ocean's Eleven." "It's Ocean's Eleven-and-a-half. Now shut up and put on your ninja suit. The piñata waits for no man."
created_at
"2026-02-08T16:02:24.178721+00:00"
Sunday, February 8th, 2026 at 4:02:24 PM GMT+00:00
model
"z-ai/glm-4.7-20251222"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1557
moderation_latency
(null)
generation_time
59264
tokens_prompt
61
tokens_completion
2169
native_tokens_prompt
66
native_tokens_completion
2171
native_tokens_completion_images
(null)
native_tokens_reasoning
1913
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
0.00478444
router
(null)
provider_responses
0
id
"2026020900012462d9545627964493"
status
200
is_byok
false
latency
1557
endpoint_id
"be4acbf5-9fcf-4332-a01d-76dfeb6d7b99"
provider_name
"Z.AI"
model_permaslug
"z-ai/glm-4.7-20251222"
api_type
"completions"
id
"gen-1770566484-nuCwCPv5N5CpTHbRUBW8"
upstream_id
"2026020900012462d9545627964493"
total_cost
0.00478444
cache_discount
0.00003136
upstream_inference_cost
0
provider_name
"Z.AI"
Evaluation details
Result
Evaluator
Details
Meta Data
81.2727%
Matches word count
n/a
neededClean
false
words
188
36.7879%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
188
wordsDialogue
188
59.0303%