1,392
Overall · rank 143 of 177
- Unit
- Arena rating, higher is better
- Range
- 1,381 to 1,402
- Sample
- 2512 votes
- Configuration
- GLM 4.6V
- 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.
1,370
Business, management and finance · rank 147 of 402
- Unit
- Arena rating, higher is better
- Range
- 1,345 to 1,395
- Sample
- 551 votes
- Configuration
- GLM 4.6V
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,350
Creative writing · rank 124 of 407
- Unit
- Arena rating, higher is better
- Range
- 1,322 to 1,379
- Sample
- 423 votes
- Configuration
- GLM 4.6V
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,394
Expert prompts · rank 111 of 359
- Unit
- Arena rating, higher is better
- Range
- 1,352 to 1,437
- Sample
- 185 votes
- Configuration
- GLM 4.6V
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,367
Instruction following · rank 146 of 409
- Unit
- Arena rating, higher is better
- Range
- 1,346 to 1,388
- Sample
- 756 votes
- Configuration
- GLM 4.6V
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,379
Overall · rank 162 of 409
- Unit
- Arena rating, higher is better
- Range
- 1,367 to 1,390
- Sample
- 2830 votes
- Configuration
- GLM 4.6V
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,357
Writing, literature and language · rank 140 of 408
- Unit
- Arena rating, higher is better
- Range
- 1,333 to 1,380
- Sample
- 625 votes
- Configuration
- GLM 4.6V
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
86.0%
Requested-length error · rank 340 of 370
- Unit
- % off the requested word count, lower is better
- Configuration
- GLM 4.6V (no reasoning)
- Measured
- 22 Dec 2025
- Not shown
- Not other format limits such as character counts or bullet counts.
35.0%
Requested-length error · rank 277 of 370
- Unit
- % off the requested word count, lower is better
- Configuration
- GLM 4.6V (thinking reasoning)
- Measured
- 22 Dec 2025
- Not shown
- Not other format limits such as character counts or bullet counts.
0.39
Style adherence · rank 43 of 370
- Unit
- score from 0 to 1, higher is better
- Configuration
- GLM 4.6V (no reasoning)
- Measured
- 22 Dec 2025
- Not shown
- Not brand voice on your own examples: UGI's prompts are private and lean towards creative writing.
0.39
Style adherence · rank 43 of 370
- Unit
- score from 0 to 1, higher is better
- Configuration
- GLM 4.6V (thinking reasoning)
- Measured
- 22 Dec 2025
- Not shown
- Not brand voice on your own examples: UGI's prompts are private and lean towards creative writing.
35.2
Writing score · rank 237 of 370
- Unit
- score out of 100, higher is better
- Configuration
- GLM 4.6V (no reasoning)
- Measured
- 22 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.
39.7
Writing score · rank 216 of 370
- Unit
- score out of 100, higher is better
- Configuration
- GLM 4.6V (thinking reasoning)
- Measured
- 22 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.
