NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ026KKC1JMSBQJXYVHVNQND
Run Details
Model:
Z.AI GLM 5.1
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
54.1s
Cost:
$0.010344
Provider:
Novita
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
66.53%
Dialogue to Total Word Ratio
(details)
83.2236%
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
"So, the entry point is the bouncy castle," Molly whispered. "Absolutely not. The structural integrity of a bouncy castle is compromised by a slight breeze, let alone my knees," Bill replied. "It's a tactical inflatable! You scale the side, execute a combat roll off the pinnacle, and land silently in the bushes by the gift table." "Or I puncture it, get trapped in a vinyl canyon, and a seven-year-old named Timmy beats me with a foam sword." "Fine. We go through the side gate. What about the guard dog?" "It's a pug, Molly." "Pugs are fiercely territorial!" "It can barely breathe, let alone mount an offensive. The real obstacle is the clown." "Right. We neutralize the clown." "I'm not fighting a clown." "We distract him with a balloon animal request. A complex one. A flamingo riding a unicycle. That buys you four minutes minimum." "What if he's a quick twister?" "Then we improvise! Grab the Lego sets, ignore the cheap goodie bags, and rendezvous at the minivan." "I still say the bouncy castle was a better exit." "The bouncy castle is a death trap, Bill. Stick to the plan. In and out before they cut the cake."
created_at
"2026-04-24T15:37:12.568Z"
4/24/2026, 3:37:12 PM
model
"z-ai/glm-5.1-20260406"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1380
moderation_latency
(null)
generation_time
53947
tokens_prompt
77
tokens_completion
2421
native_tokens_prompt
66
native_tokens_completion
2330
native_tokens_completion_images
(null)
native_tokens_reasoning
2064
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
0.0103444
router
(null)
provider_responses
0
endpoint_id
"e5835f58-53a4-4bf2-a7b6-0f4c70b56ea5"
id
"746bef86bf6505833d92411526c061b8"
is_byok
false
latency
1380
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-1777045032-sZMTSQd7K2vyUJM54H2n"
session_id
(null)
api_type
"completions"
id
"gen-1777045032-3st6bgUC0KtYgXHPuV0t"
upstream_id
"746bef86bf6505833d92411526c061b8"
total_cost
0.0103444
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Novita"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.92%
Matches word count
n/a
neededClean
false
words
197
66.53%
Dialogue to Total Word Ratio
Ratio: 97.99%, Deviation: 7.99%
neededClean
false
wordsTotal
199
wordsDialogue
195
83.2236%