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 · 2026-10-15 · rating
reka-flash-21b-20240226-online
1,143.19 rating
Confidence interval: 1,127.99 – 1,158.40
2015 votes
Category
chinese
Evaluated configuration
reka-flash-21b-20240226-online
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
reka-flash-21b-20240226-online
1,164.31 rating
Confidence interval: 1,151.61 – 1,177.02
2879 votes
Category
coding
Evaluated configuration
reka-flash-21b-20240226-online
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
reka-flash-21b-20240226-online
1,130.40 rating
Confidence interval: 1,116.07 – 1,144.72
2119 votes
Category
creative_writing
Evaluated configuration
reka-flash-21b-20240226-online
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
reka-flash-21b-20240226-online
1,180.68 rating
Confidence interval: 1,171.69 – 1,189.68
8935 votes
Category
english
Evaluated configuration
reka-flash-21b-20240226-online
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
reka-flash-21b-20240226-online
1,040.19 rating
Confidence interval: 1,029.28 – 1,051.10
10138 votes
Category
exclude_ties
Evaluated configuration
reka-flash-21b-20240226-online
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-15 · rating
reka-flash-21b-20240226-online
1,116.24 rating
Confidence interval: 1,094.98 – 1,137.49
830 votes
Category
expert
Evaluated configuration
reka-flash-21b-20240226-online
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating
reka-flash-21b-20240226-online
1,162.74 rating
Confidence interval: 1,121.81 – 1,203.68
230 votes
Category
french
Evaluated configuration
reka-flash-21b-20240226-online
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating
reka-flash-21b-20240226-online
1,150.88 rating
Confidence interval: 1,124.09 – 1,177.66
501 votes
Category
german
Evaluated configuration
reka-flash-21b-20240226-online
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
reka-flash-21b-20240226-online
1,136.75 rating
Confidence interval: 1,126.04 – 1,147.47
4506 votes
Category
hard_prompts
Evaluated configuration
reka-flash-21b-20240226-online
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
reka-flash-21b-20240226-online
1,146.66 rating
Confidence interval: 1,134.11 – 1,159.20
2928 votes
Category
hard_prompts_english
Evaluated configuration
reka-flash-21b-20240226-online
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating