NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-02-11-01KH7GSYNFNYQD2440Z6XQMHR9
Run Details
Model:
Z.AI GLM 5
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
2m 2s
Cost:
$0.014335
Provider:
Z.AI
Evaluation summary
Score
Evaluator
Details Link
95.99%
Matches word count
(details)
96.92%
Dialogue to Total Word Ratio
(details)
96.4534%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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 crouched behind the hydrangeas, the vibrations of 'The Hokey Pokey' rattling her teeth. The suburban backyard was a chaotic maze of streamers and abandoned party hats. Her eyes locked onto the prize: a mountain of wrapped gifts stacked precariously beside the ice cream stand. Bill checked his equipment, looking pale as a sheet while the sugared-up screams of six-year-olds echoed off the fence. The sheer intensity of the celebration was overwhelming, a sensory overload of primary colors and crying parents who had lost their minds. "Is the perimeter secure?" Molly whispered, adjusting her black turtleneck. "Negative," Bill replied, ducking a stray balloon. "I spotted a piñata." "Armed?" "Candy-filled. Highly volatile. We need to wait for the candle blow-out." "Agreed. The lights will dim. We have a thirty-second window." "What about the bouncy castle sentries?" "They're just kids, Bill. Jump on their heads if you have to." "I'm not jumping on kids! That's a PR nightmare." "Then use the smoke bombs. Grab the Barbie Dreamhouse and run." "It’s heavy! Can’t we just take the gift cards?" "We are professionals. We take the big score. Now, go time." Bill sighed deeply, pulling a neon party favor from his tactical pocket as they prepared to breach the heavily guarded patio.
created_at
"2026-02-11T23:34:59.281343+00:00"
2/11/2026, 11:34:59 PM
model
"z-ai/glm-5-20260211"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3123
moderation_latency
(null)
generation_time
122173
tokens_prompt
77
tokens_completion
4708
native_tokens_prompt
66
native_tokens_completion
4459
native_tokens_completion_images
(null)
native_tokens_reasoning
4362
native_tokens_cached
0
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
0.0143348
router
(null)
provider_responses
0
id
"2026021207325651a491b92e004a76"
status
200
is_byok
false
latency
3117
endpoint_id
"85146950-32c1-410b-9b81-4467d938fd16"
provider_name
"Z.AI"
model_permaslug
"z-ai/glm-5-20260211"
api_type
"completions"
id
"gen-1770852776-TFkBoHwukv4FGcRLXLi4"
upstream_id
"2026021207325651a491b92e004a76"
total_cost
0.0143348
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Z.AI"
Evaluation details
Result
Evaluator
Details
Meta Data
95.99%
Matches word count
n/a
neededClean
false
words
208
96.92%
Dialogue to Total Word Ratio
Ratio: 45.79%, Deviation: 4.21%
neededClean
false
wordsTotal
214
wordsDialogue
98
96.4534%