1,403
Overall · rank 119 of 177
- Unit
- Arena rating, higher is better
- Range
- 1,389 to 1,418
- Sample
- 1447 votes
- Configuration
- Kimi K2 0905
- Measured
- 25 Sep 2026
- Not shown
- Not an error rate: claims that cannot be checked on the web are skipped, and preference still carries most of the weight.
1,404
Business, management and finance · rank 110 of 402
- Unit
- Arena rating, higher is better
- Range
- 1,391 to 1,417
- Sample
- 2041 votes
- Configuration
- Kimi K2 0905
- 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
Creative writing · rank 94 of 407
- Unit
- Arena rating, higher is better
- Range
- 1,366 to 1,397
- Sample
- 1475 votes
- Configuration
- Kimi K2 0905
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,417
Expert prompts · rank 106 of 359
- Unit
- Arena rating, higher is better
- Range
- 1,393 to 1,441
- Sample
- 571 votes
- Configuration
- Kimi K2 0905
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,390
Instruction following · rank 125 of 409
- Unit
- Arena rating, higher is better
- Range
- 1,379 to 1,401
- Sample
- 2870 votes
- Configuration
- Kimi K2 0905
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,419
Overall · rank 110 of 409
- Unit
- Arena rating, higher is better
- Range
- 1,412 to 1,425
- Sample
- 11537 votes
- Configuration
- Kimi K2 0905
- 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 115 of 408
- Unit
- Arena rating, higher is better
- Range
- 1,370 to 1,394
- Sample
- 2564 votes
- Configuration
- Kimi K2 0905
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
22.0%
Requested-length error · rank 202 of 370
- Unit
- % off the requested word count, lower is better
- Configuration
- Kimi K2 0905
- Measured
- 15 Oct 2025
- Not shown
- Not other format limits such as character counts or bullet counts.
0.31
Style adherence · rank 315 of 370
- Unit
- score from 0 to 1, higher is better
- Configuration
- Kimi K2 0905
- Measured
- 15 Oct 2025
- Not shown
- Not brand voice on your own examples: UGI's prompts are private and lean towards creative writing.
54.4
Writing score · rank 130 of 370
- Unit
- score out of 100, higher is better
- Configuration
- Kimi K2 0905
- Measured
- 15 Oct 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.
98.6%
Answer rate · rank 76 of 108
- Unit
- % of documents, higher is better
- Configuration
- Kimi K2 0905
- 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.
17.9%
Hallucination rate · rank 97 of 108
- Unit
- % of summaries, lower is better
- Configuration
- Kimi K2 0905
- 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.
