1,388
Business, management and finance · rank 134 of 402
- Unit
- Arena rating, higher is better
- Range
- 1,374 to 1,402
- Sample
- 1798 votes
- Configuration
- R1
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,374
Creative writing · rank 113 of 407
- Unit
- Arena rating, higher is better
- Range
- 1,363 to 1,384
- Sample
- 3289 votes
- Configuration
- R1
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,402
Expert prompts · rank 127 of 359
- Unit
- Arena rating, higher is better
- Range
- 1,382 to 1,422
- Sample
- 848 votes
- Configuration
- R1
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,397
Instruction following · rank 119 of 409
- Unit
- Arena rating, higher is better
- Range
- 1,390 to 1,405
- Sample
- 6426 votes
- Configuration
- R1
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,398
Overall · rank 147 of 409
- Unit
- Arena rating, higher is better
- Range
- 1,393 to 1,403
- Sample
- 18524 votes
- Configuration
- R1
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,382
Writing, literature and language · rank 125 of 408
- Unit
- Arena rating, higher is better
- Range
- 1,374 to 1,390
- Sample
- 5355 votes
- Configuration
- R1
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
18.0%
Requested-length error · rank 150 of 370
- Unit
- % off the requested word count, lower is better
- Configuration
- R1
- Measured
- 21 Sep 2025
- Not shown
- Not other format limits such as character counts or bullet counts.
0.30
Style adherence · rank 332 of 370
- Unit
- score from 0 to 1, higher is better
- Configuration
- R1
- Measured
- 21 Sep 2025
- Not shown
- Not brand voice on your own examples: UGI's prompts are private and lean towards creative writing.
51.8
Writing score · rank 148 of 370
- Unit
- score out of 100, higher is better
- Configuration
- R1
- Measured
- 21 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.
97.0%
Answer rate · rank 88 of 108
- Unit
- % of documents, higher is better
- Configuration
- R1
- 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.
11.3%
Hallucination rate · rank 74 of 108
- Unit
- % of summaries, lower is better
- Configuration
- R1
- 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.
