NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-25-01KMJ8DDXWAR35NVCWR0WT5K6H
Run Details
Model:
Qwen 3 32B
Test:
N-Length Sentences
Scenario:
Write sentences with 10 words each
Duration:
2.2s
Cost:
$0.000464
Provider:
SambaNova
Evaluation summary
Score
Evaluator
Details Link
72.85%
Matches word count
(details)
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 storm crashed against the manor's stained-glass windows. A single candle burned in the library where he lay dead. His hand still clutched the letter sealed with crimson wax. The crack of thunder drowned the gasp of the startled maid. Detective Voss arrived, coat sodden, eyes sharp with suspicion. Portraits lined the corridor, their silences heavy with secrets. A broken clock showed minutes until the first guests arrive. The butler claimed he heard nothing beyond the storm's fury. The widow's tears fell like rain, but Voss saw a tremor in her hand. Each guest carried a past, each shadow a potential weapon. As midnight struck, the killer knew the game had just begun.
created_at
"2026-03-25T10:25:01.891Z"
3/25/2026, 10:25:01 AM
model
"qwen/qwen3-32b-04-28"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
532
moderation_latency
(null)
generation_time
2199
tokens_prompt
63
tokens_completion
597
native_tokens_prompt
45
native_tokens_completion
557
native_tokens_completion_images
(null)
native_tokens_reasoning
427
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
0.0004636
router
(null)
provider_responses
0
endpoint_id
"322b7db6-ff60-4bb1-bd02-7d8101dbe11c"
id
"12228ecd-2481-4904-a742-c47c0cf746fa"
is_byok
false
latency
531
model_permaslug
"qwen/qwen3-32b-04-28"
provider_name
"SambaNova"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer
(null)
api_type
"completions"
id
"gen-1774434301-3pqmDKzdpYSjU6v6q32H"
upstream_id
"12228ecd-2481-4904-a742-c47c0cf746fa"
total_cost
0.0004636
cache_discount
(null)
upstream_inference_cost
0
provider_name
"SambaNova"
Evaluation details
Result
Evaluator
Details
Meta Data
72.85%
Matches word count
n/a
neededClean
false
sentences
11
wordCounts
0
8
1
11
2
10
3
11
4
9
5
9
6
10
7
10
8
14
9
10
10
11