1,453
Overall · rank 18 of 44
- Unit
- Arena rating, higher is better
- Range
- 1,444 to 1,463
- Sample
- 4061 votes
- Configuration
- Gemini 3.5 Flash (high)
- Measured
- 13 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,461
Overall · rank 14 of 44
- Unit
- Arena rating, higher is better
- Range
- 1,453 to 1,468
- Sample
- 6500 votes
- Configuration
- Gemini 3.5 Flash (medium)
- Measured
- 13 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,476
Overall · rank 9 of 177
- Unit
- Arena rating, higher is better
- Range
- 1,472 to 1,479
- Sample
- 45820 votes
- Configuration
- Gemini 3.5 Flash (high)
- 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.
1,466
Overall · rank 24 of 177
- Unit
- Arena rating, higher is better
- Range
- 1,462 to 1,469
- Sample
- 44580 votes
- Configuration
- Gemini 3.5 Flash (medium)
- 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.
1,468
Business, management and finance · rank 20 of 402
- Unit
- Arena rating, higher is better
- Range
- 1,461 to 1,475
- Sample
- 9088 votes
- Configuration
- Gemini 3.5 Flash (high)
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,461
Business, management and finance · rank 27 of 402
- Unit
- Arena rating, higher is better
- Range
- 1,454 to 1,469
- Sample
- 8779 votes
- Configuration
- Gemini 3.5 Flash (medium)
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,463
Creative writing · rank 12 of 407
- Unit
- Arena rating, higher is better
- Range
- 1,455 to 1,470
- Sample
- 8808 votes
- Configuration
- Gemini 3.5 Flash (high)
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,466
Creative writing · rank 9 of 407
- Unit
- Arena rating, higher is better
- Range
- 1,458 to 1,473
- Sample
- 8744 votes
- Configuration
- Gemini 3.5 Flash (medium)
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,491
Expert prompts · rank 22 of 359
- Unit
- Arena rating, higher is better
- Range
- 1,482 to 1,500
- Sample
- 5340 votes
- Configuration
- Gemini 3.5 Flash (high)
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,487
Expert prompts · rank 28 of 359
- Unit
- Arena rating, higher is better
- Range
- 1,478 to 1,496
- Sample
- 5351 votes
- Configuration
- Gemini 3.5 Flash (medium)
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,465
Instruction following · rank 21 of 409
- Unit
- Arena rating, higher is better
- Range
- 1,459 to 1,470
- Sample
- 16713 votes
- Configuration
- Gemini 3.5 Flash (high)
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,464
Instruction following · rank 21 of 409
- Unit
- Arena rating, higher is better
- Range
- 1,458 to 1,470
- Sample
- 16384 votes
- Configuration
- Gemini 3.5 Flash (medium)
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,477
Overall · rank 19 of 409
- Unit
- Arena rating, higher is better
- Range
- 1,473 to 1,481
- Sample
- 46190 votes
- Configuration
- Gemini 3.5 Flash (high)
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,474
Overall · rank 20 of 409
- Unit
- Arena rating, higher is better
- Range
- 1,470 to 1,478
- Sample
- 44906 votes
- Configuration
- Gemini 3.5 Flash (medium)
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,472
Writing, literature and language · rank 8 of 408
- Unit
- Arena rating, higher is better
- Range
- 1,466 to 1,479
- Sample
- 11905 votes
- Configuration
- Gemini 3.5 Flash (high)
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,468
Writing, literature and language · rank 13 of 408
- Unit
- Arena rating, higher is better
- Range
- 1,462 to 1,475
- Sample
- 11987 votes
- Configuration
- Gemini 3.5 Flash (medium)
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
62.6%
Average · rank 7 of 34
- Unit
- % resolved, higher is better
- Configuration
- gemini-3.5-flash
- 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.
39.7%
Front end (SWE-Bench Multimodal) · rank 9 of 34
- Unit
- % resolved, higher is better
- Configuration
- gemini-3.5-flash
- 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.
37.5%
Greenfield (Commit0) · rank 10 of 34
- Unit
- % resolved, higher is better
- Configuration
- gemini-3.5-flash
- 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.
81.2%
Information gathering (GAIA) · rank 5 of 34
- Unit
- % resolved, higher is better
- Configuration
- gemini-3.5-flash
- 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.
78.6%
Issue resolution (SWE-Bench) · rank 4 of 34
- Unit
- % resolved, higher is better
- Configuration
- gemini-3.5-flash
- 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.
76.2%
Testing (SWT-Bench) · rank 8 of 34
- Unit
- % resolved, higher is better
- Configuration
- gemini-3.5-flash
- 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.
14.0%
Requested-length error · rank 111 of 370
- Unit
- % off the requested word count, lower is better
- Configuration
- Gemini 3.5 Flash (high)
- Measured
- 21 May 2026
- Not shown
- Not other format limits such as character counts or bullet counts.
9.0%
Requested-length error · rank 67 of 370
- Unit
- % off the requested word count, lower is better
- Configuration
- gemini-3.5-flash
- Measured
- 21 May 2026
- Not shown
- Not other format limits such as character counts or bullet counts.
12.0%
Requested-length error · rank 98 of 370
- Unit
- % off the requested word count, lower is better
- Configuration
- Gemini 3.5 Flash (medium)
- Measured
- 21 May 2026
- Not shown
- Not other format limits such as character counts or bullet counts.
13.0%
Requested-length error · rank 103 of 370
- Unit
- % off the requested word count, lower is better
- Configuration
- gemini-3.5-flash
- Measured
- 21 May 2026
- Not shown
- Not other format limits such as character counts or bullet counts.
0.34
Style adherence · rank 224 of 370
- Unit
- score from 0 to 1, higher is better
- Configuration
- Gemini 3.5 Flash (high)
- Measured
- 21 May 2026
- Not shown
- Not brand voice on your own examples: UGI's prompts are private and lean towards creative writing.
0.34
Style adherence · rank 201 of 370
- Unit
- score from 0 to 1, higher is better
- Configuration
- gemini-3.5-flash
- Measured
- 21 May 2026
- Not shown
- Not brand voice on your own examples: UGI's prompts are private and lean towards creative writing.
0.35
Style adherence · rank 173 of 370
- Unit
- score from 0 to 1, higher is better
- Configuration
- Gemini 3.5 Flash (medium)
- Measured
- 21 May 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 259 of 370
- Unit
- score from 0 to 1, higher is better
- Configuration
- gemini-3.5-flash
- Measured
- 21 May 2026
- Not shown
- Not brand voice on your own examples: UGI's prompts are private and lean towards creative writing.
69.7
Writing score · rank 26 of 370
- Unit
- score out of 100, higher is better
- Configuration
- Gemini 3.5 Flash (high)
- Measured
- 21 May 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.
72.4
Writing score · rank 11 of 370
- Unit
- score out of 100, higher is better
- Configuration
- gemini-3.5-flash
- Measured
- 21 May 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.
72.5
Writing score · rank 9 of 370
- Unit
- score out of 100, higher is better
- Configuration
- Gemini 3.5 Flash (medium)
- Measured
- 21 May 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.
72.5
Writing score · rank 10 of 370
- Unit
- score out of 100, higher is better
- Configuration
- gemini-3.5-flash
- Measured
- 21 May 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.