NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0ANNXJZCTPS0PKP8VFDCZP
Run Details
Model:
Z.AI GLM 4.5 Air
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
18.7s
Cost:
$0.000697
Provider:
Z.AI
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.9595%
Overall
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
Molly: Okay, plan's simple. We hit the party Saturday. Cake time, maximum distraction. Bill: Maximum distraction? Those kids are hyped on sugar. They'll be bouncing off the walls. Molly: That's the distraction, Bill. While they're hyperventilating over frosting, we grab the loot. Bill: Loot? It's a pile of plastic junk wrapped in paper. Who cares? Molly: We do! It's a job. Clean sweep. All presents. No leftovers. Bill: What about the clown? Guy's creepy. Saw him juggling squirrels last year. Molly: We avoid the clown. Stick to the shadows near the bounce house. Flank it. Bill: Flank the bounce house? What if someone's in it? Molly: Then wait. Patience, Bill. We wait for the piñata. Chaos then. Guaranteed. Bill: Piñata? Smack it open, candy everywhere. Perfect cover. But... what if the birthday kid opens a gift early? Molly: We improvise. You distract with terrible magic tricks. I'll grab the pile. Bill: Terrible? My disappearing coin routine's legendary. Okay, deal. Clown avoidance, bounce house flanking, piñata panic. Operation Pinata Panic. Molly: Operation Pinata Panic? Bill, that's the worst name we've ever had. Bill: It's catchy! Now, about the getaway... I know a shortcut through the neighbor's inflatable castle...
created_at
"2026-04-24T18:05:15.07Z"
4/24/2026, 6:05:15 PM
model
"z-ai/glm-4.5-air"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1256
moderation_latency
(null)
generation_time
7614
tokens_prompt
77
tokens_completion
689
native_tokens_prompt
66
native_tokens_completion
623
native_tokens_completion_images
(null)
native_tokens_reasoning
367
native_tokens_cached
6
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
0.00069748
router
(null)
provider_responses
0
endpoint_id
"f7dc79ca-bbbd-41a1-8eef-616d981ff1cb"
is_byok
false
latency
10077
model_permaslug
"z-ai/glm-4.5-air"
provider_name
"SiliconFlow"
status
504
1
endpoint_id
"c8760514-8a81-4a73-ae2c-be4942ba93f3"
id
"20260425020525b10b5ba4e55f4046"
is_byok
false
latency
1256
model_permaslug
"z-ai/glm-4.5-air"
provider_name
"Z.AI"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777053915-MnR544S75PWoK6zWkdUs"
session_id
(null)
api_type
"completions"
id
"gen-1777053915-P0TxX7w3QvuYEggNGuoD"
upstream_id
"20260425020525b10b5ba4e55f4046"
total_cost
0.00069748
cache_discount
0.00000102
upstream_inference_cost
0
provider_name
"Z.AI"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.92%
Matches word count
n/a
neededClean
false
words
197
0.00%
Dialogue to Total Word Ratio
Ratio: 0.00%, Deviation: 90.00%
neededClean
false
wordsTotal
197
wordsDialogue
0
49.9595%