NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ03YWCJKDDF9243FN37SDD5
Run Details
Model:
Z.AI GLM 4.5 Air
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
4.7s
Cost:
$0.000233
Provider:
SiliconFlow
Evaluation summary
Score
Evaluator
Details Link
68.10%
Matches word count
(details)
95.82%
Dialogue to Total Word Ratio
(details)
81.9616%
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 shimmering piñata taunted them from its perch. Molly adjusted her black balaclava, which clashed terribly with her sequined top. “I still say we go in through the bounce house,” Bill whispered, consulting a crumpled napkin with a crude map drawn on it. “We are *not* going in through the bounce house,” Molly hissed, pointing a gloved finger at the structure now filled with screaming children. “It’s a death trap. A sweaty, bouncy death trap.” “What about the petting zoo?” Bill asked, tapping a crudely drawn sheep. “They’re distracted by the baby goats. We could blend in.” “Blending in is for spies, Bill. We are professionals. We go in, we grab the loot, we get out. The presents are by the table, next to the sad-looking clown.” Just then, the clown honked a red nose directly at them. A small child pointed, giggling. “Alright, new plan,” Bill said, shoving the napkin in his pocket. “I’ll create a diversion with the face paint.” “You’re going to paint your face like a sad clown, aren’t you?” “The best kind of clown,” Bill said, already reaching for the glitter.
created_at
"2026-04-24T16:07:56.572Z"
4/24/2026, 4:07:56 PM
model
"z-ai/glm-4.5-air"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1119
moderation_latency
(null)
generation_time
4575
tokens_prompt
77
tokens_completion
303
native_tokens_prompt
70
native_tokens_completion
259
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
0.00023254
router
(null)
provider_responses
0
endpoint_id
"f7dc79ca-bbbd-41a1-8eef-616d981ff1cb"
id
"019dc03f74e5531fc0c299439bb8ad6a"
is_byok
false
latency
1119
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-1777046876-4Thy5GKS02m6dD8ZiJDi"
session_id
(null)
api_type
"completions"
id
"gen-1777046876-SYx0jA0FCDLs4UoF9Tas"
upstream_id
"019dc03f74e5531fc0c299439bb8ad6a"
total_cost
0.00023254
cache_discount
(null)
upstream_inference_cost
0
provider_name
"SiliconFlow"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
68.10%
Matches word count
n/a
neededClean
false
words
186
95.82%
Dialogue to Total Word Ratio
Ratio: 54.55%, Deviation: 4.55%
neededClean
false
wordsTotal
187
wordsDialogue
102
81.9616%