NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-02-01M1GW8H7GFT21WV3QPRSSXG69
Run Details
Model:
Z.AI GLM 5.3 (Reasoning, Max)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
50.8s
Cost:
$0.010343
Provider:
Z.AI
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
96.08%
Dialogue to Total Word Ratio
(details)
98.0311%
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
Molly peered through the bushes. "Twenty-seven kids, one bouncy castle, zero security." "Zero?" Bill said. "There's a clown." "A clown isn't security, Bill." "That clown made a balloon animal that looked exactly like my parole officer. That's a threat." "Focus. We go in as caterers." "We're not caterers." "We're wearing aprons." "Those are bibs." "Bibs, aprons—semantics. We load the presents into the van during the magic show." "Which present do we take first?" "All of them." "The one shaped like a bike?" "Especially the bike." "Fine. Bike first, then literally everything else." "You can't fit a bike in a duffel bag." "Then we wheel it out." "Wearing bibs?" "Caterer bibs. Stop asking questions." "What if the clown recognizes us?" "Why would the clown recognize us?" "Because the clown IS my parole officer." Molly stared at him. "Bill. Is that why you didn't want to do the bank job?" "The bank has that same clown. Birthday division." "Your parole officer works birthday parties as a clown?" "Side hustle. Economy's rough." "New plan. We wait for the cake." "Why?" "Because nobody—nobody—watches the presents during cake." "See, this is why you're the brains." "And Bill? Lose the bib."
created_at
"2026-09-02T10:57:27.802Z"
9/2/2026, 10:57:27 AM
model
"z-ai/glm-5.3-20260816"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3372
moderation_latency
(null)
generation_time
50763
tokens_prompt
75
tokens_completion
2182
native_tokens_prompt
73
native_tokens_completion
2344
native_tokens_completion_images
(null)
native_tokens_reasoning
2044
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
0.01034284
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788346647-IqcfoW3u1RioUa9RTy3i"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788346647-k46QObWB832wuwv5fS03"
upstream_id
"202609021857276a6e4337efe943f9"
provider_responses
0
endpoint_id
"db975786-e7f6-4838-9e56-3e0b77f1bdc2"
id
"202609021857276a6e4337efe943f9"
is_byok
false
latency
3372
model_permaslug
"z-ai/glm-5.3-20260816"
provider_name
"Z.AI"
status
200
total_cost
0.01034284
cache_discount
0.00007296
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
99.98%
Matches word count
n/a
neededClean
false
words
198
96.08%
Dialogue to Total Word Ratio
Ratio: 94.47%, Deviation: 4.47%
neededClean
false
wordsTotal
199
wordsDialogue
188
98.0311%