Models / ministral-3-14b-reasoning-2512

Mistral

ministral-3-14b-reasoning-2512

6 published results from 1 source. Each card shows where the number comes from and what it does not measure. The overall leaderboard combines them; here each stands alone.

Provider
Mistral
Sources
1
Our benchmarks
0
Price
Not yet published

Reported by others

Reported by UGI Leaderboard
44.0%
Requested-length error · rank 304 of 370
Unit
% off the requested word count, lower is better
Configuration
ministral-3-14b-reasoning-2512
Measured
8 Dec 2025
Not shown
Not other format limits such as character counts or bullet counts.
Reported by UGI Leaderboard
123.0%
Requested-length error · rank 360 of 370
Unit
% off the requested word count, lower is better
Configuration
ministral-3-14b-reasoning-2512 (think-prefill reasoning)
Measured
8 Dec 2025
Not shown
Not other format limits such as character counts or bullet counts.
Reported by UGI Leaderboard
0.35
Style adherence · rank 190 of 370
Unit
score from 0 to 1, higher is better
Configuration
ministral-3-14b-reasoning-2512
Measured
8 Dec 2025
Not shown
Not brand voice on your own examples: UGI's prompts are private and lean towards creative writing.
Reported by UGI Leaderboard
0.32
Style adherence · rank 285 of 370
Unit
score from 0 to 1, higher is better
Configuration
ministral-3-14b-reasoning-2512 (think-prefill reasoning)
Measured
8 Dec 2025
Not shown
Not brand voice on your own examples: UGI's prompts are private and lean towards creative writing.
Reported by UGI Leaderboard
25.6
Writing score · rank 302 of 370
Unit
score out of 100, higher is better
Configuration
ministral-3-14b-reasoning-2512
Measured
8 Dec 2025
Not shown
Not business copy quality: UGI's prompts are private and lean towards creative writing, and models that often refuse get no score.
Reported by UGI Leaderboard
19.2
Writing score · rank 338 of 370
Unit
score out of 100, higher is better
Configuration
ministral-3-14b-reasoning-2512 (think-prefill reasoning)
Measured
8 Dec 2025
Not shown
Not business copy quality: UGI's prompts are private and lean towards creative writing, and models that often refuse get no score.