NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ06HPNE6TF3MX513RJXE6QD
Run Details
Model:
Z.AI GLM 5.1
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
1m 46s
Cost:
$0.019047
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
86.38%
Matches word count
(details)
99.94%
Dialogue to Total Word Ratio
(details)
93.1583%
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 adjusted her tactical earpiece. Bill crouched low behind the bright pink azalea bushes, silently scanning the yard. "Target is a six-year-old's birthday bash at the Henderson house." "High security. Bouncy castle perimeter, a hired clown, and a piƱata lookout." "I have handled worse. What is the entry point?" "Side gate, but there is a balloon animal checkpoint. We will need a password." "Password is Princess Sparkle. I got it off the mom yesterday." "Nice. Disable the clown first. They are always the wildcard. Too unpredictable." "Agreed. I will use the squirt flower distraction. While he is distracted, you move on the presents." "Loot is in the dining room. Gift bags on the left, big boxes on the right. We prioritize the big boxes. I want that Barbie Dreamhouse." "What about the kids?" "What about them? They are tiny. We just walk fast." "Molly, they have sharp elbows. And they scream. It attracts the adults." "Wear earplugs. We go in, we grab the Dreamhouse, and we get out before they cut the cake. We have a three-minute window between musical chairs and the magician." "Understood. But if there is a face painter, I am aborting." "Deal. Now put on your party hat. We have a score to settle with a toddler."
created_at
"2026-04-24T16:53:10.459Z"
4/24/2026, 4:53:10 PM
model
"z-ai/glm-5.1-20260406"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3033
moderation_latency
(null)
generation_time
105478
tokens_prompt
77
tokens_completion
4962
native_tokens_prompt
66
native_tokens_completion
5430
native_tokens_completion_images
(null)
native_tokens_reasoning
4628
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
0.01904726
router
(null)
provider_responses
0
endpoint_id
"e888c44c-6a07-4a9e-bc56-cb26511865ec"
id
"chatcmpl-RcvZU1qTDW97aNrXB2qwi8jV"
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-1777049590-glERb4JEIWywAImyyasC"
session_id
(null)
api_type
"completions"
id
"gen-1777049590-DtT3wR2Qm4exQkbBvVPn"
upstream_id
"chatcmpl-RcvZU1qTDW97aNrXB2qwi8jV"
total_cost
0.01904726
cache_discount
0.000027039
upstream_inference_cost
0
provider_name
"DeepInfra"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
86.38%
Matches word count
n/a
neededClean
false
words
211
99.94%
Dialogue to Total Word Ratio
Ratio: 91.59%, Deviation: 1.59%
neededClean
false
wordsTotal
214
wordsDialogue
196
93.1583%