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 · 2026-11-09 · rating
Reka Flash 21B (Online, 20240226)
1,143.37 rating
Confidence interval: 1,128.16 – 1,158.58
2015 votes
Category
chinese
Evaluated configuration
Reka Flash 21B (Online, 20240226)
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-11-09 · rating
Reka Flash 21B (Online, 20240226)
1,164.35 rating
Confidence interval: 1,151.65 – 1,177.05
2879 votes
Category
coding
Evaluated configuration
Reka Flash 21B (Online, 20240226)
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-11-09 · rating
Reka Flash 21B (Online, 20240226)
1,130.42 rating
Confidence interval: 1,116.10 – 1,144.74
2119 votes
Category
creative_writing
Evaluated configuration
Reka Flash 21B (Online, 20240226)
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-11-09 · rating
Reka Flash 21B (Online, 20240226)
1,180.75 rating
Confidence interval: 1,171.76 – 1,189.75
8935 votes
Category
english
Evaluated configuration
Reka Flash 21B (Online, 20240226)
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-11-09 · rating
Reka Flash 21B (Online, 20240226)
1,040.22 rating
Confidence interval: 1,029.31 – 1,051.12
10138 votes
Category
exclude_ties
Evaluated configuration
Reka Flash 21B (Online, 20240226)
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-11-09 · rating
Reka Flash 21B (Online, 20240226)
1,115.92 rating
Confidence interval: 1,094.67 – 1,137.17
830 votes
Category
expert
Evaluated configuration
Reka Flash 21B (Online, 20240226)
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-11-09 · rating
Reka Flash 21B (Online, 20240226)
1,162.37 rating
Confidence interval: 1,121.46 – 1,203.29
230 votes
Category
french
Evaluated configuration
Reka Flash 21B (Online, 20240226)
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-11-09 · rating
Reka Flash 21B (Online, 20240226)
1,150.74 rating
Confidence interval: 1,123.91 – 1,177.58
501 votes
Category
german
Evaluated configuration
Reka Flash 21B (Online, 20240226)
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-11-09 · rating
Reka Flash 21B (Online, 20240226)
1,136.73 rating
Confidence interval: 1,126.02 – 1,147.44
4506 votes
Category
hard_prompts
Evaluated configuration
Reka Flash 21B (Online, 20240226)
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-11-09 · rating
Reka Flash 21B (Online, 20240226)
1,146.71 rating
Confidence interval: 1,134.17 – 1,159.26
2928 votes
Category
hard_prompts_english
Evaluated configuration
Reka Flash 21B (Online, 20240226)
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-11-09 · rating