NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ02BFMP19VVSDZSYRZRQ983
Run Details
Model:
Z.AI GLM 5.1
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
1m 57s
Cost:
$0.031654
Provider:
Novita
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
99.96%
Dialogue to Total Word Ratio
(details)
99.9775%
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
Molly adjusted her binoculars, staring at the bouncy castle through the rain-splattered windshield. The cab smelled intensely of stale coffee and terrible decisions. The neon sign for Pizza Planet buzzed furiously overhead, casting a harsh red glow over the dashboard. Bill munched loudly on a jellybean, adjusting his black ski mask and sighing. Through the window, a tiny princess swung a plastic bat at a ninja. Molly checked her watch, the second hand ticking ever closer to zero hour. She pulled a crumpled pink party invitation from her leather jacket, carefully examining the hand-drawn map to the birthday party loot. "So the target is a six-year-old?" Bill asked. "Target is a six-year-old's loot," Molly corrected. "Diamond earrings from Grandma, a PS5 from the divorced dad. It’s a treasure trove." "What about the scary clown?" "Peanuts. He’s distracted making balloon animals." "I really hate clowns, Molly." "Focus. We go in during the cake. Kids are blinded by candles. We grab the presents, then exit through the kitchen." "What if they cry?" "They're kids. They cry anyway. Remember, no violence." "But if the ninja attacks?" "Just use the water pistol." "It shoots tequila." "Exactly. It will definitely be our easiest heist yet."
created_at
"2026-04-24T15:39:52.351Z"
4/24/2026, 3:39:52 PM
model
"z-ai/glm-5.1-20260406"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1444
moderation_latency
(null)
generation_time
117397
tokens_prompt
77
tokens_completion
5840
native_tokens_prompt
66
native_tokens_completion
7173
native_tokens_completion_images
(null)
native_tokens_reasoning
6896
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
0.0316536
router
(null)
provider_responses
0
endpoint_id
"e5835f58-53a4-4bf2-a7b6-0f4c70b56ea5"
id
"ba525f1d316552db274ffc109035edee"
is_byok
false
latency
1444
model_permaslug
"z-ai/glm-5.1-20260406"
provider_name
"Novita"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777045192-OfqOdj2r6Kl8MbWueR6c"
session_id
(null)
api_type
"completions"
id
"gen-1777045192-V8oyJZPBFDpzkVlxM17k"
upstream_id
"ba525f1d316552db274ffc109035edee"
total_cost
0.0316536
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Novita"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
99.96%
Dialogue to Total Word Ratio
Ratio: 48.54%, Deviation: 1.46%
neededClean
false
wordsTotal
206
wordsDialogue
100
99.9775%