NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0558830QG5CYKJ02H9CKWD
Run Details
Model:
Z.AI GLM 4.5 Air
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
19.6s
Cost:
$0.000459
Provider:
SiliconFlow
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.0000%
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 tapped the schematics spread across the wobbly card table. "Right, the presents are over there, near the bouncy castle. Simple grab and dash." Molly peered through the window at the chaos. "Simple? Bill, look at it! There are fifteen sugar-crazed maniacs armed with plastic swords and questionable cake icing! They'll swarm us like locusts!" "We go in quiet," Bill insisted, adjusting his oversized sunglasses. "Stealth mode. Like ninjas." "Bill, you're wearing a neon green tracksuit. You stick out like a glitter-covered unicorn at a penguin convention." "Hey, it's comfortable! We'll just... slide in, grab the loot, slide out. Easy." "Easy? The last thing we 'grabbed' was Mrs. Higgins's prize-winning marrow and we ended up in her prize-winning rose bushes! We need a better plan." Bill frowned. "Fine. How about we dress as the clowns? They're already there, causing a diversion. We just... join them? Blend in?" Molly stared. "Bill, the clowns are currently sword-fighting with inflatable dinosaurs. We are *not* joining that."
created_at
"2026-04-24T16:28:53.905Z"
4/24/2026, 4:28:53 PM
model
"z-ai/glm-4.5-air"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2113
moderation_latency
(null)
generation_time
19552
tokens_prompt
77
tokens_completion
591
native_tokens_prompt
66
native_tokens_completion
523
native_tokens_completion_images
(null)
native_tokens_reasoning
274
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
0.00045902
router
(null)
provider_responses
0
endpoint_id
"f7dc79ca-bbbd-41a1-8eef-616d981ff1cb"
id
"019dc052abab8645aea7de80f7cb78f2"
is_byok
false
latency
2113
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-1777048133-CcF6lKm9h8rduGWYQTYk"
session_id
(null)
api_type
"completions"
id
"gen-1777048133-5oKRYiF5UBkq463RzDMI"
upstream_id
"019dc052abab8645aea7de80f7cb78f2"
total_cost
0.00045902
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
163
0.00%
Dialogue to Total Word Ratio
Ratio: 83.33%, Deviation: 33.33%
neededClean
false
wordsTotal
168
wordsDialogue
140
0.0000%