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
Grok 4 (0709)
1,426.47 rating
Confidence interval: 1,415.12 – 1,437.82
2826 votes
Category
chinese
Evaluated configuration
Grok 4 (0709)
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
Grok 4 (0709)
1,408.28 rating
Confidence interval: 1,401.37 – 1,415.20
8034 votes
Category
coding
Evaluated configuration
Grok 4 (0709)
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
Grok 4 (0709)
1,396.35 rating
Confidence interval: 1,387.94 – 1,404.76
5344 votes
Category
creative_writing
Evaluated configuration
Grok 4 (0709)
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
Grok 4 (0709)
1,418.07 rating
Confidence interval: 1,412.89 – 1,423.25
17562 votes
Category
english
Evaluated configuration
Grok 4 (0709)
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
Grok 4 (0709)
1,395.49 rating
Confidence interval: 1,390.18 – 1,400.80
28652 votes
Category
exclude_ties
Evaluated configuration
Grok 4 (0709)
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-28 · rating
Grok 4 (0709)
1,414.63 rating
Confidence interval: 1,401.52 – 1,427.73
2072 votes
Category
expert
Evaluated configuration
Grok 4 (0709)
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating
Grok 4 (0709)
1,418.40 rating
Confidence interval: 1,393.48 – 1,443.32
591 votes
Category
french
Evaluated configuration
Grok 4 (0709)
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating
Grok 4 (0709)
1,428.57 rating
Confidence interval: 1,408.56 – 1,448.59
905 votes
Category
german
Evaluated configuration
Grok 4 (0709)
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
Grok 4 (0709)
1,408.74 rating
Confidence interval: 1,403.73 – 1,413.75
19372 votes
Category
hard_prompts
Evaluated configuration
Grok 4 (0709)
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
Grok 4 (0709)
1,410.30 rating
Confidence interval: 1,403.60 – 1,417.01
8814 votes
Category
hard_prompts_english
Evaluated configuration
Grok 4 (0709)
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating