NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHY8JN7RR1FX4Y78P5CNQSSM
Run Details
Model:
Ministral 3 3B
Test:
N-Length Sentences
Scenario:
Write sentences with 10 words each
Duration:
732ms
Cost:
$0.000016
Provider:
Mistral
Evaluation summary
Score
Evaluator
Details Link
81.86%
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 moon casts eerie shadows across the grand, abandoned mansion. Glowing lanterns flicker weakly in the dark, cold hallway. A single key lies forgotten on the crumbling marble floor. Whispers echo through the halls, though no one seems to hear. The clock ticks loudly, its hands frozen at midnight. Every creak of the floorboards feels like a warning. A locked door stands between the living and the dead. Someone must have left behind a deadly, hidden secret. The air grows thick with tension, suffocating and dreadful. Every shadow hides a possibility of a terrible deed.
created_at
"2026-02-20T19:31:40.932Z"
2/20/2026, 7:31:40 PM
model
"mistralai/ministral-3b-2512"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
303
moderation_latency
(null)
generation_time
603
tokens_prompt
46
tokens_completion
151
native_tokens_prompt
39
native_tokens_completion
124
native_tokens_completion_images
(null)
native_tokens_reasoning
0
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
0.0000163
router
(null)
provider_responses
0
endpoint_id
"b9f6828f-aef9-498a-91f5-6816fbf72420"
id
"c83a7873ecb64c91b278e0ff62fe1f9e"
is_byok
false
latency
291
model_permaslug
"mistralai/ministral-3b-2512"
provider_name
"Mistral"
status
200
api_type
"completions"
id
"gen-1771615900-tnbmYYlyabfT8L3T7Ji7"
upstream_id
"c83a7873ecb64c91b278e0ff62fe1f9e"
total_cost
0.0000163
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Mistral"
Evaluation details
Result
Evaluator
Details
Meta Data
81.86%
Matches word count
n/a
neededClean
false
sentences
10
wordCounts
0
10
1
9
2
10
3
11
4
9
5
9
6
10
7
9
8
9
9
9