NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHYADD28AWYF4D6ASPGBR2F3
Run Details
Model:
Ministral 3 3B
Test:
N-Length Sentences
Scenario:
Write sentences with 5 words each
Duration:
850ms
Cost:
$0.000017
Provider:
Mistral
Evaluation summary
Score
Evaluator
Details Link
55.93%
Matches word count
(details)
Model input
User/Human
Please write the opening scene of a murder mystery where each sentence has exactly 5 words. Please make sure that each sentence has the same length. Only return the opening itself.
Model response
Messages
Meta
AI
The clock struck midnight softly. Moonlight spilled through curtains thin. A whisper slithered through hallway dark. Footsteps paused, then vanished quick. Someone stood near the door’s edge. A key turned with a sharp, cold click. Gasps rose from the room’s quiet. A body lay still, eyes wide open. Blood pooled beneath the victim’s skin. The detective stepped forward, keen. A single note lay on the table. Words scrawled in ink black. *"They know too much—don’t trust him yet."* The pen was sharp, the hand steady. Who left this message? Who’s next?
created_at
"2026-02-20T20:03:45.874Z"
2/20/2026, 8:03:45 PM
model
"mistralai/ministral-3b-2512"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
225
moderation_latency
(null)
generation_time
740
tokens_prompt
46
tokens_completion
155
native_tokens_prompt
38
native_tokens_completion
129
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
0.0000167
router
(null)
provider_responses
0
endpoint_id
"b9f6828f-aef9-498a-91f5-6816fbf72420"
id
"c0027741c7ba4e2594726db8a806f7ac"
is_byok
false
latency
225
model_permaslug
"mistralai/ministral-3b-2512"
provider_name
"Mistral"
status
200
api_type
"completions"
id
"gen-1771617825-HFW8LRsisUW0sk4bHd8i"
upstream_id
"c0027741c7ba4e2594726db8a806f7ac"
total_cost
0.0000167
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Mistral"
Evaluation details
Result
Evaluator
Details
Meta Data
55.93%
Matches word count
n/a
neededClean
false
sentences
16
wordCounts
0
5
1
5
2
6
3
5
4
6
5
8
6
6
7
7
8
6
9
5
10
7
11
5
12
8
13
7
14
4
15
2