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
Ring-flash-2.0
1,398.48 rating
Confidence interval: 1,371.90 – 1,425.07
442 votes
Category
chinese
Evaluated configuration
Ring-flash-2.0
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
Ring-flash-2.0
1,366.12 rating
Confidence interval: 1,351.26 – 1,380.98
1506 votes
Category
coding
Evaluated configuration
Ring-flash-2.0
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
Ring-flash-2.0
1,269.86 rating
Confidence interval: 1,250.21 – 1,289.51
888 votes
Category
creative_writing
Evaluated configuration
Ring-flash-2.0
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
Ring-flash-2.0
1,367.00 rating
Confidence interval: 1,356.54 – 1,377.46
3058 votes
Category
english
Evaluated configuration
Ring-flash-2.0
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
Ring-flash-2.0
1,285.29 rating
Confidence interval: 1,275.09 – 1,295.49
4961 votes
Category
exclude_ties
Evaluated configuration
Ring-flash-2.0
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-28 · rating
Ring-flash-2.0
1,342.94 rating
Confidence interval: 1,312.24 – 1,373.64
359 votes
Category
expert
Evaluated configuration
Ring-flash-2.0
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
Ring-flash-2.0
1,344.28 rating
Confidence interval: 1,334.46 – 1,354.11
3542 votes
Category
hard_prompts
Evaluated configuration
Ring-flash-2.0
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
Ring-flash-2.0
1,377.60 rating
Confidence interval: 1,363.09 – 1,392.11
1593 votes
Category
hard_prompts_english
Evaluated configuration
Ring-flash-2.0
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating