1,259
Business, management and finance · rank 276 of 402
- Unit
- Arena rating, higher is better
- Range
- 1,244 to 1,275
- Sample
- 1443 votes
- Configuration
- Mistral Small 3
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,227
Creative writing · rank 286 of 407
- Unit
- Arena rating, higher is better
- Range
- 1,214 to 1,239
- Sample
- 2415 votes
- Configuration
- Mistral Small 3
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,259
Expert prompts · rank 261 of 359
- Unit
- Arena rating, higher is better
- Range
- 1,238 to 1,280
- Sample
- 754 votes
- Configuration
- Mistral Small 3
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,255
Instruction following · rank 286 of 409
- Unit
- Arena rating, higher is better
- Range
- 1,247 to 1,264
- Sample
- 5485 votes
- Configuration
- Mistral Small 3
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,274
Overall · rank 289 of 409
- Unit
- Arena rating, higher is better
- Range
- 1,268 to 1,280
- Sample
- 14681 votes
- Configuration
- Mistral Small 3
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,248
Writing, literature and language · rank 289 of 408
- Unit
- Arena rating, higher is better
- Range
- 1,238 to 1,258
- Sample
- 3942 votes
- Configuration
- Mistral Small 3
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
8.0%
Requested-length error · rank 55 of 370
- Unit
- % off the requested word count, lower is better
- Configuration
- Mistral Small 3
- Measured
- 6 Sep 2025
- Not shown
- Not other format limits such as character counts or bullet counts.
0.35
Style adherence · rank 182 of 370
- Unit
- score from 0 to 1, higher is better
- Configuration
- Mistral Small 3
- Measured
- 6 Sep 2025
- Not shown
- Not brand voice on your own examples: UGI's prompts are private and lean towards creative writing.
33.9
Writing score · rank 245 of 370
- Unit
- score out of 100, higher is better
- Configuration
- Mistral Small 3
- Measured
- 6 Sep 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.
97.9%
Answer rate · rank 83 of 108
- Unit
- % of documents, higher is better
- Configuration
- Mistral Small 3
- 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.
5.1%
Hallucination rate · rank 10 of 108
- Unit
- % of summaries, lower is better
- Configuration
- Mistral Small 3
- 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.
