NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-25-01KMJ7V95149ENCT8CGWRPBC55
Run Details
Model:
Qwen 3 32B
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
24.9s
Cost:
$0.000260
Provider:
Nebius
Evaluation summary
Score
Evaluator
Details Link
20.38%
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 storm broke at midnight, and the lighthouse keeper found a body washed up on the jagged rocks below. The victim’s wedding ring glinted under the moonlight, though no one claimed to know their name or their history. A note, half-burned and scribbled with frantic words, lay clutched in the hand that had once gripped a cold glass of brandy. Neighbors swore they heard a struggle at precisely 2:17 a.m., but the storm’s howl erased every trace of footsteps in the sand. The lighthouse, long abandoned for modern technology, had become a haven for secrets buried beneath rusted lanterns. A local detective arrived, her coat soaked through, eyes scanning the scene with the calm of someone who’d seen too many endings. Her partner, a younger officer with an ink-stained notebook, pointed to the victim’s fingers: “No soil under the nails,” he muttered. Nearby, a bottle of expensive wine rolled in the tide, cork missing, though no glasses bore its deep red stain. A child’s toy lay ten feet away, half-buried in the sand, its paint chipped but grinning—unnervingly untouched by the surf. The tide rolled in, whispering, while the town slept and the stars above seemed unbothered by the weight of the body on the shore.
created_at
"2026-03-25T10:15:07.173Z"
3/25/2026, 10:15:07 AM
model
"qwen/qwen3-32b-04-28"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
297
moderation_latency
(null)
generation_time
24846
tokens_prompt
63
tokens_completion
978
native_tokens_prompt
45
native_tokens_completion
853
native_tokens_completion_images
(null)
native_tokens_reasoning
656
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
0.0002604
router
(null)
provider_responses
0
endpoint_id
"aaa39b6c-e488-491a-91e4-e5fb66f86601"
id
"cmpl-b95abd267e5a0cc6"
is_byok
false
latency
297
model_permaslug
"qwen/qwen3-32b-04-28"
provider_name
"Nebius"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer
(null)
api_type
"completions"
id
"gen-1774433707-pejZBez5w8lDTH7njKRD"
upstream_id
"cmpl-b95abd267e5a0cc6"
total_cost
0.0002604
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Nebius"
Evaluation details
Result
Evaluator
Details
Meta Data
20.38%
Matches word count
n/a
neededClean
false
sentences
8
wordCounts
0
19
1
19
2
22
3
22
4
17
5
22
6
62
7
24