1,420
Overall · rank 113 of 177
- Unit
- Arena rating, higher is better
- Range
- 1,416 to 1,424
- Sample
- 28454 votes
- Configuration
- Qwen3.5-27B
- 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.
1,408
Business, management and finance · rank 110 of 402
- Unit
- Arena rating, higher is better
- Range
- 1,400 to 1,416
- Sample
- 5600 votes
- Configuration
- Qwen3.5-27B
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,358
Creative writing · rank 139 of 407
- Unit
- Arena rating, higher is better
- Range
- 1,348 to 1,367
- Sample
- 4306 votes
- Configuration
- Qwen3.5-27B
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,441
Expert prompts · rank 90 of 359
- Unit
- Arena rating, higher is better
- Range
- 1,429 to 1,453
- Sample
- 2649 votes
- Configuration
- Qwen3.5-27B
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,400
Instruction following · rank 116 of 409
- Unit
- Arena rating, higher is better
- Range
- 1,394 to 1,407
- Sample
- 9215 votes
- Configuration
- Qwen3.5-27B
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,409
Overall · rank 126 of 409
- Unit
- Arena rating, higher is better
- Range
- 1,404 to 1,413
- Sample
- 28640 votes
- Configuration
- Qwen3.5-27B
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,380
Writing, literature and language · rank 128 of 408
- Unit
- Arena rating, higher is better
- Range
- 1,372 to 1,388
- Sample
- 6489 votes
- Configuration
- Qwen3.5-27B
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
11.0%
Requested-length error · rank 91 of 370
- Unit
- % off the requested word count, lower is better
- Configuration
- qwen3.5-27b
- Measured
- 9 Mar 2026
- Not shown
- Not other format limits such as character counts or bullet counts.
19.0%
Requested-length error · rank 163 of 370
- Unit
- % off the requested word count, lower is better
- Configuration
- qwen3.5-27b
- Measured
- 8 Mar 2026
- Not shown
- Not other format limits such as character counts or bullet counts.
0.31
Style adherence · rank 310 of 370
- Unit
- score from 0 to 1, higher is better
- Configuration
- qwen3.5-27b
- Measured
- 9 Mar 2026
- Not shown
- Not brand voice on your own examples: UGI's prompts are private and lean towards creative writing.
0.33
Style adherence · rank 249 of 370
- Unit
- score from 0 to 1, higher is better
- Configuration
- qwen3.5-27b
- Measured
- 8 Mar 2026
- Not shown
- Not brand voice on your own examples: UGI's prompts are private and lean towards creative writing.
42.4
Writing score · rank 195 of 370
- Unit
- score out of 100, higher is better
- Configuration
- qwen3.5-27b
- Measured
- 9 Mar 2026
- Not shown
- Not business copy quality: UGI's prompts are private and lean towards creative writing, and models that often refuse get no score.
39.9
Writing score · rank 215 of 370
- Unit
- score out of 100, higher is better
- Configuration
- qwen3.5-27b
- Measured
- 8 Mar 2026
- Not shown
- Not business copy quality: UGI's prompts are private and lean towards creative writing, and models that often refuse get no score.
99.8%
Answer rate · rank 34 of 108
- Unit
- % of documents, higher is better
- Configuration
- Qwen3.5-27B
- 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.
12.1%
Hallucination rate · rank 81 of 108
- Unit
- % of summaries, lower is better
- Configuration
- Qwen3.5-27B
- 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.
