NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-06-24-01KVX2WZK2BGM3KBZK2494Y9P2
Run Details
Model:
Z.AI GLM 5.2 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
1m 44s
Cost:
$0.040763
Provider:
Z.AI
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.9902%
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 adjusted her binoculars, surveying the suburban fortress. The target was a large backyard swarming with seven-year-old savages hopped up on cake. In the center sat the prize: a mountain of wrapped boxes, gleaming under the afternoon sun like pirate gold. Bill crouched beside her in the azaleas, his black tactical turtleneck inappropriate for the July heat. "How do we bypass that clown?" Bill asked. "Just chew a balloon until it pops," Molly replied. "Is that some sort of code?" Bill whispered. Molly rolled her eyes, ignoring his confusion. The clown in question was a formidable adversary, twisting latex into weaponized poodles with terrifying speed. They needed a distraction. Molly checked her watch. The piñata phase was approaching. That was their window. Once the papier-mâché donkey was breached, chaos would reign, and the guards—the exhausted parents sipping stale coffee—would be entirely focused on preventing a sugar-induced fatality. Molly signaled Bill to ready the grappling hook, which was actually just a pool noodle with a rope tied to it. If timed right, they could snag the gift table and drag it into the hydrangeas before anyone noticed. Bill nodded, gripping the noodle with sweaty palms, ready to ruin a child's birthday.
created_at
"2026-06-24T15:10:11.566Z"
6/24/2026, 3:10:11 PM
model
"z-ai/glm-5.2-20260616"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3040
moderation_latency
(null)
generation_time
103526
tokens_prompt
77
tokens_completion
7652
native_tokens_prompt
73
native_tokens_completion
9241
native_tokens_completion_images
(null)
native_tokens_reasoning
8970
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"
service_tier
(null)
usage
0.0407626
router
(null)
provider_responses
0
endpoint_id
"442ea97f-ad5e-40d5-b9a6-66e9e0417dce"
id
"202606242310116c195d4f76d44c84"
is_byok
false
latency
3040
model_permaslug
"z-ai/glm-5.2-20260616"
provider_name
"Z.AI"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.16.0; linux; x64))"
http_referer
(null)
request_id
"req-1782313811-PsgUfEenic7DXa9SAgEO"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1782313811-ykIfTmv1D2dQsWfgE4B8"
upstream_id
"202606242310116c195d4f76d44c84"
total_cost
0.0407626
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Z.AI"
response_cache_source_id
(null)
data_region
"global"
Evaluation details
Result
Evaluator
Details
Meta Data
99.98%
Matches word count
n/a
neededClean
false
words
202
100.00%
Dialogue to Total Word Ratio
Ratio: 9.22%, Deviation: 0.78%
neededClean
false
wordsTotal
206
wordsDialogue
19
99.9902%