NC Bench
Overview
About
Tests
Models
Model
Z.AI GLM 4.6
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2026-02-08-01KGYXV2TXY5WZNG0X4XF65AP4
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
“Entry point is the ‘Pin the Tail’ station. Bill, focus.” “Sorry. Do you think they’ll have those little hot dogs? The ones in the croissant rolls?” “The objective is the gift table. Fast, hard, no tears.” “Tears? Molly, we’re stealing from children. The biggest risk is a glitter bomb.” “Which is why I’m creating a diversion. I’ll challenge the birthday boy to a dance-off. You grab the loot. What’s the exit?” “The bouncy castle. We launch ourselves over the fence. They’ll never see it coming.” “Absolutely not. Grab, run, minivan. And we are not stopping for cake, Bill.” “But it’s probably ice cream cake. That’s a tactical energy resource.” “Fine. One slice. After the presents are secured. Now, check your gear. You got the industrial-strength gift tag remover?” “Bill, you brought a crowbar.” “It’s for stubborn ribbons.”
created_at
"2026-02-08T15:28:10.36686+00:00"
Sunday, February 8th, 2026 at 3:28:10 PM GMT+00:00
model
"z-ai/glm-4.6"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2336
moderation_latency
(null)
generation_time
34643
tokens_prompt
61
tokens_completion
1645
native_tokens_prompt
66
native_tokens_completion
1654
native_tokens_completion_images
(null)
native_tokens_reasoning
1477
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
0.0028951399999776
router
(null)
provider_responses
0
id
"chatcmpl-RBuLXhBP3kxU66DrQ2PhX1Wr"
status
200
is_byok
false
latency
65
endpoint_id
"c8607edc-8577-4199-b03d-1213da4743dc"
provider_name
"DeepInfra"
model_permaslug
"z-ai/glm-4.6"
api_type
"completions"
id
"gen-1770564455-PEpVTnik2knSaT9DBkPt"
upstream_id
"chatcmpl-RBuLXhBP3kxU66DrQ2PhX1Wr"
total_cost
0.0028951399999776
cache_discount
0.0000112000000224
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
0.0000%
Matches word count
n/a
neededClean
false
words
139
36.7879%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
139
wordsDialogue
139
18.3940%