NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM08XJM5N855X8XMXCZ740JH
Run Details
Model:
Mistral Small 4 (Reasoning)
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
39.7s
Cost:
$0.004746
Provider:
Mistral
Evaluation summary
Score
Evaluator
Details Link
88.76%
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
Rainpoured relentlessly against the ancient, creaking windows of the isolated mansion, each droplet echoing ominously like a funeral drum. The violent, unrelenting storm raged outside, its howling winds rattling the fragile glass panes of the grand hall's towering doors. Inside, the weary old butler adjusted his stiff black tie nervously as time dragged, knowing tonight's gathering held unexpected dangers. The first guest arrived late, her sharp heels clicking on the polished marble floor, eyes darting around the cavernous hallway. The second guest, a tall man with piercing eyes, carried a mysterious leather case out of place at this gathering. Whispers among the staff hinted darkly at a secret tied to this manor, but none dared speak of the rumors openly. An unearthly scream shrieked through the hollow mansion, twisting the tense silence into palpable fear among the terrified guests present.
created_at
"2026-03-18T10:47:31.224Z"
3/18/2026, 10:47:31 AM
model
"mistralai/mistral-small-2603"
1/1/2603, 12:00:00 AM
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
346
moderation_latency
(null)
generation_time
39535
tokens_prompt
46
tokens_completion
6817
native_tokens_prompt
51
native_tokens_completion
7898
native_tokens_completion_images
(null)
native_tokens_reasoning
6580
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
0.00474645
router
(null)
provider_responses
0
endpoint_id
"f5ed6283-4e17-457d-98cd-2ec0c318171d"
id
"d14109cc36a440deb02e1ee1c35c8017"
is_byok
false
latency
341
model_permaslug
"mistralai/mistral-small-2603"
1/1/2603, 12:00:00 AM
provider_name
"Mistral"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer
(null)
api_type
"completions"
id
"gen-1773830851-KpNUZHsLRptKbRvbqd6G"
upstream_id
"d14109cc36a440deb02e1ee1c35c8017"
total_cost
0.00474645
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Mistral"
Evaluation details
Result
Evaluator
Details
Meta Data
88.76%
Matches word count
n/a
neededClean
false
sentences
7
wordCounts
0
19
1
20
2
20
3
20
4
20
5
21
6
20