NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-06-24-01KVX2MC8PDSSHGKXV96HD32KA
Run Details
Model:
Z.AI GLM 5.2 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
22.9s
Cost:
$0.005802
Provider:
Z.AI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Count dialogue tags
(details)
Model input
User/Human
You are an expert novel writer in the cozy mystery genre. Write a scene of about 200 words, with dialogue between two characters. The dialogue should be unattributed, meaning the speaker is not explicitly mentioned. The scene should be set in a small town bakery. Only return the story, nothing else.
Model response
Messages
Meta
AI
The scent of toasted pecans and warm vanilla hung heavy in the air as a damp rag swiped rhythmically across the glass display case. "Did you hear about the mayor's missing brooch?" "Mm. A lemon tart, please. And no, I try not to listen to village chatter before noon." "It's practically noon right now. Look at the grandfather clock. Besides, Agnes saw the whole thing from the post office window." "Agnes needs a new hobby. A stronger coffee, too." "She said he was wearing that ridiculous tweed coat. The one with the deep pockets." "Lots of people wear tweed around here." "Not in July, they don't. Especially not while sprinting past the rose garden." "Sprinting? At his age?" "Exactly my point! A man with a bad knee doesn't run unless he's hiding something. Or stealing it." "You sound like you're writing a penny dreadful. Box up two almond croissants, would you?" "Fine, ignore the evidence. But when Sheriff Miller starts asking questions, don't come crying to me." "I wouldn't dream of it. Just put the croissants in the brown paper bag." "He bought blueberry muffins this morning, you know. The sheriff. Two of them. Looked pale as uncooked dough."
created_at
"2026-06-24T15:05:29.634Z"
6/24/2026, 3:05:29 PM
model
"z-ai/glm-5.2-20260616"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3056
moderation_latency
(null)
generation_time
22699
tokens_prompt
81
tokens_completion
1411
native_tokens_prompt
74
native_tokens_completion
1295
native_tokens_completion_images
(null)
native_tokens_reasoning
1022
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
0.0058016
router
(null)
provider_responses
0
endpoint_id
"442ea97f-ad5e-40d5-b9a6-66e9e0417dce"
id
"20260624230529490c6d02697641a9"
is_byok
false
latency
3056
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-1782313529-s1CXMU08c0idBZu39lRu"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1782313529-EgDCHFZbZLdw4FLH8XA2"
upstream_id
"20260624230529490c6d02697641a9"
total_cost
0.0058016
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
100.00%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)