NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-25-01KMJ8VZW25RSDAK9FWPG0G811
Run Details
Model:
Qwen 3 32B
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
5.5s
Cost:
$0.000124
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
2.71%
Matches word count
(details)
Model input
User/Human
Please write the opening scene of a murder mystery where each sentence has exactly 20 words. Please make sure that each sentence has the same length. Only return the opening itself.
Model response
Messages
Meta
AI
The clock tower struck midnight as snow began to fall, but the hands never moved. A body lay sprawled in the town square, crimson scarf now a useless accessory. No blood, no wound, and yet the crowd muttered how this man once breathed. He had vanished a week ago, resurfaced only in this icy embrace. Detective Elara Voss arrived, coat frayed, face pale under the lamplight’s brittle glow. She noted the frosted teacup clutched in his stiffening hand and the thin trail of steam long gone. The bartender claimed he ordered a brandy but drank it black; groundskeeper swore he sometimes raged at shadows, sometimes whispered secrets only the crows understood. An anonymous letter arrived that morning, postmarked with a town that no longer exists. The victim’s daughter wept in the gallery where he displayed his unsold paintings, each canvas smeared with red streaks that resembled screams. The coroner declared time of death as one minute after the clock tower’s last chime.
created_at
"2026-03-25T10:32:59.015Z"
3/25/2026, 10:32:59 AM
model
"qwen/qwen3-32b-04-28"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
151
moderation_latency
(null)
generation_time
5424
tokens_prompt
63
tokens_completion
512
native_tokens_prompt
45
native_tokens_completion
430
native_tokens_completion_images
(null)
native_tokens_reasoning
266
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
0.000124
router
(null)
provider_responses
0
endpoint_id
"6b8c829d-3094-45e7-8139-0a67e09060c3"
id
"cmpl-f911d983f08e43849a1101f3e52428ac"
is_byok
false
latency
84
model_permaslug
"qwen/qwen3-32b-04-28"
provider_name
"DeepInfra"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer
(null)
api_type
"completions"
id
"gen-1774434779-s7Gau4lCcNhA5Y7yRDGP"
upstream_id
"cmpl-f911d983f08e43849a1101f3e52428ac"
total_cost
0.000124
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
2.71%
Matches word count
n/a
neededClean
false
sentences
10
wordCounts
0
15
1
14
2
14
3
12
4
13
5
18
6
25
7
14
8
22
9
15