NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-02-08-01KGYZ60AQ118SKNWEVMNSDQNK
Run Details
Model:
Z.AI GLM 4.6
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
2m 29s
Cost:
$0.009171
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
77.08%
Dialogue to Total Word Ratio
(details)
38.5407%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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
Bill peered through binoculars at a rainbow-colored bouncy castle sagging across the street. Tiny humans screamed inside. Beside him, Molly unfolded a hand-drawn blueprint, her expression grim. She viciously circled the 'prize piñata' with a red pen. He pouted, gesturing towards a mountain of presents, his eyes fixated on a giant box wrapped in sparkling dinosaur paper. Molly rubbed her temples. Bill pulled a shiny gold kazoo from his jacket pocket, looking immensely proud as he tooted a mournful, off-key note. The heist was already a disaster. “So, the piñata is the diversion?” Bill whispered. “I call whacking it.” “You’re not whacking anything,” she hissed. “You’re on balloon duty. A loud pop at precisely 3:04 PM draws the parents. I’ll grab the loot.” “But what about the big one? With the enormous bow?” “That’s the primary target, you idiot,” Molly snapped, “the ‘Giga-Gorilla.’ Now, focus. Do you have the kazoo?” “For the signal,” he whispered defensively, holding it up. “It’s more subtle than a balloon.”
created_at
"2026-02-08T15:53:31.168104+00:00"
2/8/2026, 3:53:31 PM
model
"z-ai/glm-4.6"
4/6/2001, 12:00:00 AM
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
255
moderation_latency
(null)
generation_time
148953
tokens_prompt
61
tokens_completion
5249
native_tokens_prompt
66
native_tokens_completion
5267
native_tokens_completion_images
(null)
native_tokens_reasoning
4954
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
0.0091705599999552
router
(null)
provider_responses
0
id
"chatcmpl-RrrqX1IlkFTEJ2ZDMq7ljvOX"
status
200
is_byok
false
latency
64
endpoint_id
"c8607edc-8577-4199-b03d-1213da4743dc"
provider_name
"DeepInfra"
model_permaslug
"z-ai/glm-4.6"
4/6/2001, 12:00:00 AM
api_type
"completions"
id
"gen-1770565861-d1tbSt7FNxH4H0nKHief"
upstream_id
"chatcmpl-RrrqX1IlkFTEJ2ZDMq7ljvOX"
total_cost
0.0091705599999552
cache_discount
0.0000224000000448
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
165
77.08%
Dialogue to Total Word Ratio
Ratio: 42.86%, Deviation: 7.14%
neededClean
false
wordsTotal
168
wordsDialogue
72
38.5407%