Only the same benchmark, version, workload, scenario and unit share a row. Missing results are not zero. System results include the full submitted hardware and software configuration.
Arena text preference / chinesehuman preference · 2026-10-28 · rating
FastChat-T5 3B
718.82 rating
Confidence interval: 681.56 – 756.07
224 votes
Category
chinese
Evaluated configuration
FastChat-T5 3B
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
FastChat-T5 3B
763.61 rating
Confidence interval: 734.23 – 792.99
428 votes
Category
coding
Evaluated configuration
FastChat-T5 3B
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
FastChat-T5 3B
901.82 rating
Confidence interval: 878.51 – 925.14
744 votes
Category
creative_writing
Evaluated configuration
FastChat-T5 3B
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
FastChat-T5 3B
934.58 rating
Confidence interval: 921.31 – 947.85
3442 votes
Category
english
Evaluated configuration
FastChat-T5 3B
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
FastChat-T5 3B
634.88 rating
Confidence interval: 616.19 – 653.56
2836 votes
Category
exclude_ties
Evaluated configuration
FastChat-T5 3B
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
FastChat-T5 3B
814.09 rating
Confidence interval: 793.41 – 834.77
797 votes
Category
hard_prompts
Evaluated configuration
FastChat-T5 3B
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
FastChat-T5 3B
829.73 rating
Confidence interval: 807.16 – 852.30
690 votes
Category
hard_prompts_english
Evaluated configuration
FastChat-T5 3B
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating