NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-15-01KKS2SFSQ1FNHZX76Z7YMC2QB
Run Details
Model:
Z.AI GLM 5 Turbo
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
1m 2s
Cost:
$0.026731
Provider:
Z.AI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
100.0000%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 unrolled the stolen architectural blueprint across the dingy motel table, her expression deadly serious despite the crayon drawn dragons decorating the margins. Bill adjusted his ski mask, sweating profusely in the stuffy room while studying the perimeter defenses. Target Alpha was a suburban backyard currently swarming with highly unpredictable subjects. These were not your standard security guards. These were seven year olds hopped up on refined sugar and adrenaline. One wrong move meant a barrage of sticky fruit punch and a deafening shriek alarm that would summon heavily armed parental units. Bill traced a gloved finger over the primary infiltration point. The inflatable fortress was a structural liability, offering zero acoustic cover but maximum bounce velocity for a rapid extraction. He tapped the payload location, a pile of wrapped cardboard boxes sitting unguarded on the patio. The sheer volume of Barbies and Lego sets would easily net them a fortune at the downtown pawn shop. Molly checked her watch, firmly confirming the timeline. The entertainer distraction was scheduled to arrive in four minutes, creating the perfect window of chaos. "We go through the bouncy castle." "Then we take every single present and run." "No dumb mistakes." "Absolutely none whatsoever."
created_at
"2026-03-15T15:45:44.766Z"
3/15/2026, 3:45:44 PM
model
"z-ai/glm-5-turbo-20260315"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1427
moderation_latency
(null)
generation_time
61854
tokens_prompt
77
tokens_completion
7312
native_tokens_prompt
66
native_tokens_completion
8349
native_tokens_completion_images
(null)
native_tokens_reasoning
8107
native_tokens_cached
64
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.026731008
router
(null)
provider_responses
0
endpoint_id
"9ce3b132-3a17-4fea-8092-0e8e519ed32b"
id
"202603152345455c71211a66e749a2"
is_byok
false
latency
1427
model_permaslug
"z-ai/glm-5-turbo-20260315"
provider_name
"Z.AI"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer
(null)
api_type
"completions"
id
"gen-1773589544-2F5lkjqFTljyiKhF42wO"
upstream_id
"202603152345455c71211a66e749a2"
total_cost
0.026731008
cache_discount
0.00006144
upstream_inference_cost
0
provider_name
"Z.AI"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
100.00%
Dialogue to Total Word Ratio
Ratio: 10.00%, Deviation: 0.00%
neededClean
false
wordsTotal
200
wordsDialogue
20
100.0000%