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
1,135.32 rating
Confidence interval: 1,121.82 – 1,148.83
2774 votes
Category
chinese
Evaluated configuration
reka-flash-21b-20240226
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
reka-flash-21b-20240226
1,153.47 rating
Confidence interval: 1,142.87 – 1,164.08
4748 votes
Category
coding
Evaluated configuration
reka-flash-21b-20240226
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
reka-flash-21b-20240226
1,123.70 rating
Confidence interval: 1,111.57 – 1,135.82
3490 votes
Category
creative_writing
Evaluated configuration
reka-flash-21b-20240226
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
reka-flash-21b-20240226
1,179.01 rating
Confidence interval: 1,171.67 – 1,186.35
14444 votes
Category
english
Evaluated configuration
reka-flash-21b-20240226
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
reka-flash-21b-20240226
1,031.92 rating
Confidence interval: 1,022.73 – 1,041.11
16076 votes
Category
exclude_ties
Evaluated configuration
reka-flash-21b-20240226
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-15 · rating
reka-flash-21b-20240226
1,107.02 rating
Confidence interval: 1,089.90 – 1,124.15
1325 votes
Category
expert
Evaluated configuration
reka-flash-21b-20240226
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating
reka-flash-21b-20240226
1,174.39 rating
Confidence interval: 1,142.93 – 1,205.84
430 votes
Category
french
Evaluated configuration
reka-flash-21b-20240226
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating
reka-flash-21b-20240226
1,152.66 rating
Confidence interval: 1,130.91 – 1,174.40
798 votes
Category
german
Evaluated configuration
reka-flash-21b-20240226
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
reka-flash-21b-20240226
1,136.39 rating
Confidence interval: 1,127.58 – 1,145.20
7446 votes
Category
hard_prompts
Evaluated configuration
reka-flash-21b-20240226
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
reka-flash-21b-20240226
1,144.03 rating
Confidence interval: 1,133.58 – 1,154.48
4796 votes
Category
hard_prompts_english
Evaluated configuration
reka-flash-21b-20240226
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating