NC Bench
Overview
About
Tests
Models
Model
Z.AI GLM 4.6
Test
N-Length Sentences
Scenario
Write sentences with 10 words each
Run ID
2026-02-08-01KGYYZ4CXG0FTMN68JC1H5WJ7
Model input
User/Human
Please write the opening scene of a murder mystery where each sentence has exactly 10 words. Please make sure that each sentence has the same length. Only return the opening itself.
Model response
Messages
Meta
AI
The heavy oak doors swung open without a single sound. Detective Miles Corbin stepped into the dimly lit library. He smelled old paper and something else entirely new. Across the room, a body lay sprawled on the floor. Lord Ashworth’s face was a mask of pure surprise. A small ornate dagger was plunged deep in his chest. Corbin did not touch anything, just observed the whole scene. The fireplace had burned out sometime early this morning. An expensive-looking book lay open just beside his hand. Miles knew this case would be his most difficult yet.
created_at
"2026-02-08T15:47:52.610938+00:00"
Sunday, February 8th, 2026 at 3:47:52 PM GMT+00:00
model
"z-ai/glm-4.6"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
400
moderation_latency
(null)
generation_time
35637
tokens_prompt
35
tokens_completion
1236
native_tokens_prompt
40
native_tokens_completion
1244
native_tokens_completion_images
(null)
native_tokens_reasoning
1176
native_tokens_cached
16
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
0.0021761599999888
router
(null)
provider_responses
0
id
"chatcmpl-RvC8GBDIyq8wZSuMYnXsTNFc"
status
200
is_byok
false
latency
59
endpoint_id
"c8607edc-8577-4199-b03d-1213da4743dc"
provider_name
"DeepInfra"
model_permaslug
"z-ai/glm-4.6"
api_type
"completions"
id
"gen-1770565636-pYfTQxc96PI2yurSP5cn"
upstream_id
"chatcmpl-RvC8GBDIyq8wZSuMYnXsTNFc"
total_cost
0.0021761599999888
cache_discount
0.0000056000000112
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
89.6327%
Matches word count
n/a
neededClean
false
sentences
10
wordCounts
0
10
1
9
2
9
3
10
4
9
5
10
6
10
7
9
8
10
9
10