1,444
Overall · rank 54 of 177
- Unit
- Arena rating, higher is better
- Range
- 1,438 to 1,450
- Sample
- 11773 votes
- Configuration
- GLM 4.7
- 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.
1,442
Business, management and finance · rank 51 of 402
- Unit
- Arena rating, higher is better
- Range
- 1,430 to 1,455
- Sample
- 2288 votes
- Configuration
- GLM 4.7
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,404
Creative writing · rank 72 of 407
- Unit
- Arena rating, higher is better
- Range
- 1,391 to 1,418
- Sample
- 1955 votes
- Configuration
- GLM 4.7
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,449
Expert prompts · rank 70 of 359
- Unit
- Arena rating, higher is better
- Range
- 1,429 to 1,469
- Sample
- 809 votes
- Configuration
- GLM 4.7
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,425
Instruction following · rank 71 of 409
- Unit
- Arena rating, higher is better
- Range
- 1,415 to 1,436
- Sample
- 3310 votes
- Configuration
- GLM 4.7
- 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
Overall · rank 72 of 409
- Unit
- Arena rating, higher is better
- Range
- 1,435 to 1,448
- Sample
- 12217 votes
- Configuration
- GLM 4.7
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,416
Writing, literature and language · rank 71 of 408
- Unit
- Arena rating, higher is better
- Range
- 1,405 to 1,427
- Sample
- 2818 votes
- Configuration
- GLM 4.7
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
42.3%
Average · rank 26 of 34
- Unit
- % resolved, higher is better
- Configuration
- glm-4.7
- Measured
- 30 Jun 2026
- Not shown
- Not the model alone: the score is for the model inside the OpenHands agent, at the SDK version shown.
22.1%
Front end (SWE-Bench Multimodal) · rank 30 of 34
- Unit
- % resolved, higher is better
- Configuration
- glm-4.7
- Measured
- 30 Jun 2026
- Not shown
- Not the model alone: the score is for the model inside the OpenHands agent, at the SDK version shown.
12.5%
Greenfield (Commit0) · rank 25 of 34
- Unit
- % resolved, higher is better
- Configuration
- glm-4.7
- Measured
- 30 Jun 2026
- Not shown
- Not the model alone: the score is for the model inside the OpenHands agent, at the SDK version shown.
53.9%
Information gathering (GAIA) · rank 20 of 34
- Unit
- % resolved, higher is better
- Configuration
- glm-4.7
- Measured
- 30 Jun 2026
- Not shown
- Not the model alone: the score is for the model inside the OpenHands agent, at the SDK version shown.
73.4%
Issue resolution (SWE-Bench) · rank 20 of 34
- Unit
- % resolved, higher is better
- Configuration
- glm-4.7
- Measured
- 30 Jun 2026
- Not shown
- Not the model alone: the score is for the model inside the OpenHands agent, at the SDK version shown.
49.4%
Testing (SWT-Bench) · rank 26 of 34
- Unit
- % resolved, higher is better
- Configuration
- glm-4.7
- Measured
- 30 Jun 2026
- Not shown
- Not the model alone: the score is for the model inside the OpenHands agent, at the SDK version shown.
28.0%
Requested-length error · rank 243 of 370
- Unit
- % off the requested word count, lower is better
- Configuration
- glm-4.7
- Measured
- 22 Dec 2025
- Not shown
- Not other format limits such as character counts or bullet counts.
33.0%
Requested-length error · rank 267 of 370
- Unit
- % off the requested word count, lower is better
- Configuration
- glm-4.7
- Measured
- 22 Dec 2025
- Not shown
- Not other format limits such as character counts or bullet counts.
0.37
Style adherence · rank 104 of 370
- Unit
- score from 0 to 1, higher is better
- Configuration
- glm-4.7
- Measured
- 22 Dec 2025
- Not shown
- Not brand voice on your own examples: UGI's prompts are private and lean towards creative writing.
0.38
Style adherence · rank 67 of 370
- Unit
- score from 0 to 1, higher is better
- Configuration
- glm-4.7
- Measured
- 22 Dec 2025
- Not shown
- Not brand voice on your own examples: UGI's prompts are private and lean towards creative writing.
44.2
Writing score · rank 181 of 370
- Unit
- score out of 100, higher is better
- Configuration
- glm-4.7
- 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.
47.4
Writing score · rank 167 of 370
- Unit
- score out of 100, higher is better
- Configuration
- glm-4.7
- 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.
99.8%
Answer rate · rank 34 of 108
- Unit
- % of documents, higher is better
- Configuration
- GLM 4.7
- 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.
11.7%
Hallucination rate · rank 75 of 108
- Unit
- % of summaries, lower is better
- Configuration
- GLM 4.7
- 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.
