NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ05FT2M21Z6PQ3Q29H1K84S
Run Details
Model:
Z.AI GLM 5.1
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
2m 49s
Cost:
$0.013433
Provider:
AtlasCloud
Evaluation summary
Score
Evaluator
Details Link
98.71%
Matches word count
(details)
65.21%
Dialogue to Total Word Ratio
(details)
81.9622%
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 we go in through the bouncy castle?" Bill asked. "No, Bill. The bouncy castle is inflated. You can't just walk through the plastic wall." "What if we bring a sharp knife?" "Absolutely not. We are not popping a bouncy castle full of seven-year-olds. That is a line even we do not cross." "Fine. What about the piƱata rope? We climb that?" "Also no. It's attached to a flimsy tree branch." "Look, I'm just saying, the presents are stacked right next to the clown. It is a high-risk target zone." "Which is exactly why we wait for the cake. When they turn off the lights to sing Happy Birthday, we move." "What if the clown spots us in the dark?" "He won't. He'll be making a balloon animal." "What if he throws it at us?" "Then you catch it and keep running toward the loot." "What kind of animal? I don't want a worm." "It's a dog, Bill. Clown animals are always dogs." "What about the parents?" "Distracted by the veggie tray and the boxed wine." "And the birthday boy?" "He'll be crying because we stole his Lego sets." "Should we leave him something?" "Like what?" "A balloon dog?" "Just get the bags, Bill," Molly said.
created_at
"2026-04-24T16:36:49.858Z"
4/24/2026, 4:36:49 PM
model
"z-ai/glm-5.1-20260406"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3419
moderation_latency
(null)
generation_time
38595
tokens_prompt
77
tokens_completion
2989
native_tokens_prompt
66
native_tokens_completion
3032
native_tokens_completion_images
(null)
native_tokens_reasoning
2753
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
0.01343254
router
(null)
provider_responses
0
endpoint_id
"7e919c5e-6c06-4182-adaf-2910d5d4b5a8"
id
"7374ec372d124efb80c6c8bbd06ddad0"
is_byok
false
latency
3419
model_permaslug
"z-ai/glm-5.1-20260406"
provider_name
"AtlasCloud"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777048609-w2yQjBtHpKstuVwl89nO"
session_id
(null)
api_type
"completions"
id
"gen-1777048609-23qBAe89t7k4PyoB5w2A"
upstream_id
"7374ec372d124efb80c6c8bbd06ddad0"
total_cost
0.01343254
cache_discount
(null)
upstream_inference_cost
0
provider_name
"AtlasCloud"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
98.71%
Matches word count
n/a
neededClean
false
words
206
65.21%
Dialogue to Total Word Ratio
Ratio: 98.09%, Deviation: 8.09%
neededClean
false
wordsTotal
209
wordsDialogue
205
81.9622%