Models / Ministral 3 14B 2512
MistralMinistral 3 14B 2512
8 published results from 2 sources. Each card shows where the number comes from and what it does not measure. Results are never combined into one score.
- Provider
- Mistral
- Sources
- 2
- Our benchmarks
- 0
- Price
- Not yet published
Reported by others
24.0%
Requested-length error · rank 217 of 370
- Unit
- % off the requested word count, lower is better
- Configuration
- Ministral 3 14B 2512
- Measured
- 3 Dec 2025
- Not shown
- Not other format limits such as character counts or bullet counts.
58.0%
Requested-length error · rank 319 of 370
- Unit
- % off the requested word count, lower is better
- Configuration
- Ministral 3 14B 2512 (think-prefill reasoning)
- Measured
- 3 Dec 2025
- Not shown
- Not other format limits such as character counts or bullet counts.
0.32
Style adherence · rank 277 of 370
- Unit
- score from 0 to 1, higher is better
- Configuration
- Ministral 3 14B 2512
- Measured
- 3 Dec 2025
- Not shown
- Not brand voice on your own examples: UGI's prompts are private and lean towards creative writing.
0.31
Style adherence · rank 305 of 370
- Unit
- score from 0 to 1, higher is better
- Configuration
- Ministral 3 14B 2512 (think-prefill reasoning)
- Measured
- 3 Dec 2025
- Not shown
- Not brand voice on your own examples: UGI's prompts are private and lean towards creative writing.
31.4
Writing score · rank 265 of 370
- Unit
- score out of 100, higher is better
- Configuration
- Ministral 3 14B 2512
- Measured
- 3 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.
25.7
Writing score · rank 298 of 370
- Unit
- score out of 100, higher is better
- Configuration
- Ministral 3 14B 2512 (think-prefill reasoning)
- Measured
- 3 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.
99.6%
Answer rate · rank 48 of 108
- Unit
- % of documents, higher is better
- Configuration
- Ministral 3 14B 2512
- Measured
- 22 Sep 2026
- Not shown
- Not a quality score: a low rate usually means content filters were triggered, and hallucination rates are measured on answered documents only.
19.4%
Hallucination rate · rank 101 of 108
- Unit
- % of summaries, lower is better
- Configuration
- Ministral 3 14B 2512
- Measured
- 22 Sep 2026
- Not shown
- Not errors in open questions or other tasks: only summarisation, judged by Vectara's own model (HHEM-2.3), not by people, on news-style documents rather than your data.
Compare Ministral 3 14B 2512 with
