NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ08SFV1JQ9XNRC354S21HCT
Run Details
Model:
Z.AI GLM 4.5 Air
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
8.3s
Cost:
$0.000208
Provider:
SiliconFlow
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.0011%
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
"The candy cane security is a joke," Molly whispered, adjusting her balaclava. "It's the clowns I'm worried about. They've got shifty eyes." "Clowns are professionals, Molly," Bill hissed back, polishing a pair of novelty oversized glasses. "Their job is to distract while the real work gets done. We'll be in and out before the piƱata even gets whacked." "And what about the presents? The good stuff." Molly gestured towards the brightly wrapped mountain of gifts under the tree. "That's the easy part. I've got a device." Bill proudly held up a magnetic ribbon dispenser. "We just walk in, look official, and slap these on. The wrapping paper does all the work." "It better," Molly grumbled. "If I have to wear this getup any longer, I'm going to develop a permanent fear of red noses. Now, on three. One... two..." A high-pitched squeal cut her off. "Look! The entertainers are here!" A tiny voice yelled, pointing right at them. "It's the Shrimpy Brothers!"
created_at
"2026-04-24T17:32:22.765Z"
4/24/2026, 5:32:22 PM
model
"z-ai/glm-4.5-air"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
4796
moderation_latency
(null)
generation_time
8132
tokens_prompt
77
tokens_completion
250
native_tokens_prompt
70
native_tokens_completion
231
native_tokens_completion_images
(null)
native_tokens_reasoning
0
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
num_fetches
(null)
web_search_engine
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.00020846
router
(null)
provider_responses
0
endpoint_id
"f7dc79ca-bbbd-41a1-8eef-616d981ff1cb"
id
"019dc08cd10b21642b22a0162293dc70"
is_byok
false
latency
4796
model_permaslug
"z-ai/glm-4.5-air"
provider_name
"SiliconFlow"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777051942-VloWmPQHtyCGY0v676WN"
session_id
(null)
api_type
"completions"
id
"gen-1777051942-PCyrvVE7ENt7Wkh6l1wi"
upstream_id
"019dc08cd10b21642b22a0162293dc70"
total_cost
0.00020846
cache_discount
(null)
upstream_inference_cost
0
provider_name
"SiliconFlow"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
162
0.00%
Dialogue to Total Word Ratio
Ratio: 68.10%, Deviation: 18.10%
neededClean
false
wordsTotal
163
wordsDialogue
111
0.0011%