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 Fast (Non-Reasoning)
1,456.96 rating
Confidence interval: 1,428.59 – 1,485.33
463 votes
Category
chinese
Evaluated configuration
Grok 4 Fast (Non-Reasoning)
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
Grok 4 Fast (Non-Reasoning)
1,427.93 rating
Confidence interval: 1,411.24 – 1,444.62
1182 votes
Category
coding
Evaluated configuration
Grok 4 Fast (Non-Reasoning)
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
Grok 4 Fast (Non-Reasoning)
1,386.26 rating
Confidence interval: 1,366.30 – 1,406.22
889 votes
Category
creative_writing
Evaluated configuration
Grok 4 Fast (Non-Reasoning)
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
Grok 4 Fast (Non-Reasoning)
1,413.72 rating
Confidence interval: 1,402.36 – 1,425.07
2641 votes
Category
english
Evaluated configuration
Grok 4 Fast (Non-Reasoning)
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
Grok 4 Fast (Non-Reasoning)
1,390.12 rating
Confidence interval: 1,379.45 – 1,400.78
4549 votes
Category
exclude_ties
Evaluated configuration
Grok 4 Fast (Non-Reasoning)
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-28 · rating
Grok 4 Fast (Non-Reasoning)
1,398.40 rating
Confidence interval: 1,364.25 – 1,432.54
288 votes
Category
expert
Evaluated configuration
Grok 4 Fast (Non-Reasoning)
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
Grok 4 Fast (Non-Reasoning)
1,411.86 rating
Confidence interval: 1,401.19 – 1,422.54
3011 votes
Category
hard_prompts
Evaluated configuration
Grok 4 Fast (Non-Reasoning)
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
Grok 4 Fast (Non-Reasoning)
1,417.86 rating
Confidence interval: 1,401.39 – 1,434.33
1267 votes
Category
hard_prompts_english
Evaluated configuration
Grok 4 Fast (Non-Reasoning)
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating