NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-02-01M1H5JV9ZQ94YY2B8S6TDJF06
Run Details
Model:
Z.AI GLM 5.3 Flash (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
15.2s
Cost:
$0.000078
Provider:
Z.AI
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
0.59%
Dialogue to Total Word Ratio
(details)
50.2558%
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
The crawl space under Lucky Pete's Party Palace smelled like birthday cake and regret. Molly spread the blueprints across a plastic table shaped like a dinosaur. "So the presents will be in the gift corner," Bill said, tapping the map. "Right next to the ball pit." "And you're wearing the clown nose why, exactly?" "Disguise, Molly. Nobody suspects a clown." "Everyone suspects a clown now, Bill. It's the first rule of the modern era." He tucked the nose into his pocket, sulking. "Fine. Then what's my role?" "You're my nephew. Greedy, sugar-loaded, unable to walk in a straight line. Method acting." Bill frowned. "How old am I?" "Nine. Committed to the bit." They studied the layout. Two exits, one bouncy castle, a diaper station nobody wanted near. "The kids get presents at three sharp," Molly said. "We swap the bags at two-forty-five. In, out, done before the pinata breaks." "What if a kid cries?" "Kids cry at these things regardless. It's ambient noise." Bill nodded slowly. "And the pony?" Molly froze. "There's a pony?" "Apparently. His name is Buttercup." She sighed and rolled up the blueprints. "Every job has a pony, Bill. Every single job." "Buttercup complicates things," Bill said. "Buttercup always does."
created_at
"2026-09-02T13:40:22.982Z"
9/2/2026, 1:40:22 PM
model
"z-ai/glm-5.3-flash-20260826"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
4456
moderation_latency
(null)
generation_time
15194
tokens_prompt
75
tokens_completion
329
native_tokens_prompt
73
native_tokens_completion
306
native_tokens_completion_images
(null)
native_tokens_reasoning
8
native_tokens_cached
64
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"
service_tier
(null)
usage
0.000078135
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788356422-RIZEt2yqusHpEdNkj0SZ"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788356422-k38JQoxdFlAB1MthIQ0X"
upstream_id
"20260902214023d31393d2c799404d"
provider_responses
0
endpoint_id
"8e9fe48b-2f91-41c3-a8a7-e4a93a8c4ff0"
id
"20260902214023d31393d2c799404d"
is_byok
false
latency
4456
model_permaslug
"z-ai/glm-5.3-flash-20260826"
provider_name
"Z.AI"
status
200
total_cost
0.000078135
cache_discount
0.00000768
upstream_inference_cost
0
provider_name
"Z.AI"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
99.92%
Matches word count
n/a
neededClean
false
words
203
0.59%
Dialogue to Total Word Ratio
Ratio: 65.05%, Deviation: 15.05%
neededClean
false
wordsTotal
206
wordsDialogue
134
50.2558%