NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ047JRVJ75H7TKHJTKSVMS6
Run Details
Model:
Z.AI GLM 5.1
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
1m 46s
Cost:
$0.017973
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
93.65%
Matches word count
(details)
64.96%
Dialogue to Total Word Ratio
(details)
79.3056%
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 target is a princess bounce house?" Molly asked. "No, the target is inside the princess bounce house. The presents are under the imported cake table," Bill corrected. "Cake table. Got it. What's the primary entry point?" "The side gate. Padlock code is 1-2-3-4. Left the latch loose." "Complete amateurs. What about perimeter security?" "A clown. Named Twinkles." "Armed or unarmed?" "Balloon animals. And a foam piƱata stick. He's ruthless." "Understood. What's the extraction plan?" "Grab the Barbie dreamhouse, avoid the sticky fingers, exit quietly through the petting zoo." "Expected casualties?" "Only if we have to physically take down a seven-year-old." "Lethal force is completely off the table, Bill." "Fine. I'll bring the tactical silly string." "That's a weapon of mass distraction. What about the ice cream truck getaway driver?" "He's parked out back. We got exactly three minutes before the sugar rush hits." "What if they cry?" "They're supposed to cry, Molly. We're stealing their birthday presents." "Right. I still feel bad about the pony from the last job." "The pony wasn't part of the heist. Leave the pony this time." "Okay. Masks on?" "Masks on. Remember, grab the wrapped boxes, ignore the goody bags, and whatever you do, do not look the clown in the eyes."
created_at
"2026-04-24T16:12:41.641Z"
4/24/2026, 4:12:41 PM
model
"z-ai/glm-5.1-20260406"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2050
moderation_latency
(null)
generation_time
106244
tokens_prompt
77
tokens_completion
4484
native_tokens_prompt
66
native_tokens_completion
5123
native_tokens_completion_images
(null)
native_tokens_reasoning
4144
native_tokens_cached
32
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
0.01797276
router
(null)
provider_responses
0
endpoint_id
"e888c44c-6a07-4a9e-bc56-cb26511865ec"
id
"chatcmpl-Rqlken714CDo6VmO4xm9UBRO"
is_byok
false
latency
109
model_permaslug
"z-ai/glm-5.1-20260406"
provider_name
"DeepInfra"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777047161-Tt25v2TTAG47foZeqxb9"
session_id
(null)
api_type
"completions"
id
"gen-1777047161-mdG7Nn7HYGX3tVF984Ko"
upstream_id
"chatcmpl-Rqlken714CDo6VmO4xm9UBRO"
total_cost
0.01797276
cache_discount
0.000027039
upstream_inference_cost
0
provider_name
"DeepInfra"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
93.65%
Matches word count
n/a
neededClean
false
words
209
64.96%
Dialogue to Total Word Ratio
Ratio: 98.10%, Deviation: 8.10%
neededClean
false
wordsTotal
211
wordsDialogue
207
79.3056%