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
Reka Flash (20240904)
1,220.67 rating
Confidence interval: 1,197.54 – 1,243.79
607 votes
Category
chinese
Evaluated configuration
Reka Flash (20240904)
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
Reka Flash (20240904)
1,189.69 rating
Confidence interval: 1,174.52 – 1,204.86
1207 votes
Category
coding
Evaluated configuration
Reka Flash (20240904)
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
Reka Flash (20240904)
1,201.92 rating
Confidence interval: 1,184.47 – 1,219.37
1037 votes
Category
creative_writing
Evaluated configuration
Reka Flash (20240904)
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
Reka Flash (20240904)
1,222.80 rating
Confidence interval: 1,213.70 – 1,231.91
4032 votes
Category
english
Evaluated configuration
Reka Flash (20240904)
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
Reka Flash (20240904)
1,102.46 rating
Confidence interval: 1,090.59 – 1,114.33
4562 votes
Category
exclude_ties
Evaluated configuration
Reka Flash (20240904)
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-28 · rating
Reka Flash (20240904)
1,181.69 rating
Confidence interval: 1,158.60 – 1,204.77
493 votes
Category
expert
Evaluated configuration
Reka Flash (20240904)
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating
Reka Flash (20240904)
1,178.32 rating
Confidence interval: 1,139.70 – 1,216.94
207 votes
Category
german
Evaluated configuration
Reka Flash (20240904)
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
Reka Flash (20240904)
1,181.30 rating
Confidence interval: 1,170.14 – 1,192.46
2289 votes
Category
hard_prompts
Evaluated configuration
Reka Flash (20240904)
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
Reka Flash (20240904)
1,186.12 rating
Confidence interval: 1,172.26 – 1,199.99
1389 votes
Category
hard_prompts_english
Evaluated configuration
Reka Flash (20240904)
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating