Models / GPT-5

OpenAI

GPT-5

18 published results from 3 sources. Each card shows where the number comes from and what it does not measure. Results are never combined into one score.

Provider
OpenAI
Sources
3
Our benchmarks
0
Price
Not yet published

Reported by others

Reported by Arena (formerly LMArena)
1,183
Overall · rank 12 of 34
Unit
Arena rating, higher is better
Range
1,175 to 1,190
Sample
20781 votes
Configuration
GPT-5
Measured
24 Aug 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
Reported by Arena (formerly LMArena)
1,421
Overall · rank 107 of 177
Unit
Arena rating, higher is better
Range
1,414 to 1,428
Sample
6877 votes
Configuration
GPT-5 (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.
Reported by Arena (formerly LMArena)
1,413
Business, management and finance · rank 107 of 402
Unit
Arena rating, higher is better
Range
1,405 to 1,422
Sample
5515 votes
Configuration
GPT-5 (high)
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
Reported by Arena (formerly LMArena)
1,373
Creative writing · rank 118 of 407
Unit
Arena rating, higher is better
Range
1,363 to 1,382
Sample
4199 votes
Configuration
GPT-5 (high)
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
Reported by Arena (formerly LMArena)
1,460
Expert prompts · rank 59 of 359
Unit
Arena rating, higher is better
Range
1,444 to 1,475
Sample
1667 votes
Configuration
GPT-5 (high)
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
Reported by Arena (formerly LMArena)
1,410
Instruction following · rank 100 of 409
Unit
Arena rating, higher is better
Range
1,403 to 1,417
Sample
8293 votes
Configuration
GPT-5 (high)
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
Reported by Arena (formerly LMArena)
1,435
Overall · rank 85 of 409
Unit
Arena rating, higher is better
Range
1,430 to 1,439
Sample
31503 votes
Configuration
GPT-5 (high)
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
Reported by Arena (formerly LMArena)
1,397
Writing, literature and language · rank 96 of 408
Unit
Arena rating, higher is better
Range
1,389 to 1,404
Sample
6975 votes
Configuration
GPT-5 (high)
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
Reported by UGI Leaderboard
58.0%
Requested-length error · rank 319 of 370
Unit
% off the requested word count, lower is better
Configuration
GPT-5 (high)
Measured
24 Sep 2025
Not shown
Not other format limits such as character counts or bullet counts.
Reported by UGI Leaderboard
92.0%
Requested-length error · rank 344 of 370
Unit
% off the requested word count, lower is better
Configuration
gpt-5
Measured
24 Sep 2025
Not shown
Not other format limits such as character counts or bullet counts.
Reported by UGI Leaderboard
0.39
Style adherence · rank 40 of 370
Unit
score from 0 to 1, higher is better
Configuration
GPT-5 (high)
Measured
24 Sep 2025
Not shown
Not brand voice on your own examples: UGI's prompts are private and lean towards creative writing.
Reported by UGI Leaderboard
0.37
Style adherence · rank 97 of 370
Unit
score from 0 to 1, higher is better
Configuration
gpt-5
Measured
24 Sep 2025
Not shown
Not brand voice on your own examples: UGI's prompts are private and lean towards creative writing.
Reported by UGI Leaderboard
53.5
Writing score · rank 138 of 370
Unit
score out of 100, higher is better
Configuration
GPT-5 (high)
Measured
24 Sep 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.
Reported by UGI Leaderboard
48.3
Writing score · rank 165 of 370
Unit
score out of 100, higher is better
Configuration
gpt-5
Measured
24 Sep 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.
Reported by Vectara Hallucination Leaderboard
99.9%
Answer rate · rank 19 of 108
Unit
% of documents, higher is better
Configuration
GPT-5 (high)
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.
Reported by Vectara Hallucination Leaderboard
99.9%
Answer rate · rank 19 of 108
Unit
% of documents, higher is better
Configuration
gpt-5
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.
Reported by Vectara Hallucination Leaderboard
15.1%
Hallucination rate · rank 95 of 108
Unit
% of summaries, lower is better
Configuration
GPT-5 (high)
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.
Reported by Vectara Hallucination Leaderboard
14.7%
Hallucination rate · rank 93 of 108
Unit
% of summaries, lower is better
Configuration
gpt-5
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.

Compare GPT-5 with