NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0101RMYRESN1REHS36QX17
Run Details
Model:
Z.AI GLM 4.5 Air
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
10.3s
Cost:
$0.000512
Provider:
Novita
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
79.78%
Dialogue to Total Word Ratio
(details)
39.8884%
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
"Alright, the van's parked three blocks down, Molly," Bill whispered, checking his watch. "We go in ten minutes." "Good. Remember the plan? Distract the clown, I grab the presents, you cover the exits." "Clown distraction. Got it. Maybe I juggle some eggs?" "Eggs? Bill, no! Too messy. Use the whoopee cushions." "Whoopi cushions? Perfect! Classic. Hey, what about the piƱata? Could I swing that at the clown?" "No, Bill! Too suspicious. Focus. And don't step on any Lego." "Ooh, sharp edges. Got it. What if a kid sees me?" "You're wearing the oversized fake mustache, right?" "Yep. Big. Black. Ridiculous. Like the one from last week's bank job." "Bill, we rob bakeries, not banks. Remember?" "Right. Bakery. Presents. Clown. Got it." "Bill..." "Yeah?" "The presents are under the table. Snatch and go." "On it. I'll be stealthy. Like a ninja... with a mustache." "Bill, just be quiet. And whatever you do, don't eat the cake." "Aw, man. That's the best part!"
created_at
"2026-04-24T15:16:09.122Z"
4/24/2026, 3:16:09 PM
model
"z-ai/glm-4.5-air"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
573
moderation_latency
(null)
generation_time
10106
tokens_prompt
77
tokens_completion
656
native_tokens_prompt
66
native_tokens_completion
595
native_tokens_completion_images
(null)
native_tokens_reasoning
402
native_tokens_cached
18
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
0.00051244
router
(null)
provider_responses
0
endpoint_id
"90fc9bb3-01bb-419f-bb58-dea60a80d201"
id
"06ea4fe1be8402adb37d6b40dd0357db"
is_byok
false
latency
571
model_permaslug
"z-ai/glm-4.5-air"
provider_name
"Novita"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777043769-C72v8K3W76B3fnoeJmHq"
session_id
(null)
api_type
"completions"
id
"gen-1777043769-N3CloF1nF5bHWJgMXMUy"
upstream_id
"06ea4fe1be8402adb37d6b40dd0357db"
total_cost
0.00051244
cache_discount
0.00000189
upstream_inference_cost
0
provider_name
"Novita"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
161
79.78%
Dialogue to Total Word Ratio
Ratio: 96.89%, Deviation: 6.89%
neededClean
false
wordsTotal
161
wordsDialogue
156
39.8884%