GeekRadar / The comparison desk
COMPARE.
AI models
xai

Grok 4.1

Model evaluation

Capability & preference

Human preference · Arena

Overall text preferences from head-to-head votes. Not factual accuracy or a task-success rate.

Grok 4.1 1436.0 Grok 4.1 · 95% interval 1432.8–1439.1 · 68,599 votes · 2026-10-28

Recorded results

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 4.1

1,464.62 rating

Confidence interval: 1,456.02 – 1,473.22

5311 votes

Category
chinese
Evaluated configuration
Grok 4.1
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating

Grok 4.1

1,443.72 rating

Confidence interval: 1,438.26 – 1,449.18

16002 votes

Category
coding
Evaluated configuration
Grok 4.1
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating

Grok 4.1

1,410.96 rating

Confidence interval: 1,404.36 – 1,417.56

10072 votes

Category
creative_writing
Evaluated configuration
Grok 4.1
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating

Grok 4.1

1,446.38 rating

Confidence interval: 1,442.00 – 1,450.76

29032 votes

Category
english
Evaluated configuration
Grok 4.1
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating

Grok 4.1

1,430.60 rating

Confidence interval: 1,426.33 – 1,434.88

49641 votes

Category
exclude_ties
Evaluated configuration
Grok 4.1
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-28 · rating

Grok 4.1

1,411.11 rating

Confidence interval: 1,402.56 – 1,419.65

5091 votes

Category
expert
Evaluated configuration
Grok 4.1
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating

Grok 4.1

1,444.35 rating

Confidence interval: 1,429.11 – 1,459.59

1791 votes

Category
french
Evaluated configuration
Grok 4.1
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating

Grok 4.1

1,446.15 rating

Confidence interval: 1,428.58 – 1,463.73

1249 votes

Category
german
Evaluated configuration
Grok 4.1
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating

Grok 4.1

1,435.30 rating

Confidence interval: 1,431.36 – 1,439.24

39442 votes

Category
hard_prompts
Evaluated configuration
Grok 4.1
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating

Grok 4.1

1,440.16 rating

Confidence interval: 1,434.82 – 1,445.51

17038 votes

Category
hard_prompts_english
Evaluated configuration
Grok 4.1
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating

Grok 4.1

1,422.89 rating

Confidence interval: 1,416.95 – 1,428.83

13074 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
Grok 4.1
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating

Grok 4.1

1,405.46 rating

Confidence interval: 1,399.50 – 1,411.42

12943 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
Grok 4.1
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating

Grok 4.1

1,444.98 rating

Confidence interval: 1,436.17 – 1,453.79

5044 votes

Category
industry_legal_and_government
Evaluated configuration
Grok 4.1
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating

Grok 4.1

1,442.15 rating

Confidence interval: 1,435.94 – 1,448.36

11125 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
Grok 4.1
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating

Grok 4.1

1,406.64 rating

Confidence interval: 1,396.40 – 1,416.89

3585 votes

Category
industry_mathematical
Evaluated configuration
Grok 4.1
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating

Grok 4.1

1,442.00 rating

Confidence interval: 1,432.76 – 1,451.25

4568 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
Grok 4.1
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating

Grok 4.1

1,449.54 rating

Confidence interval: 1,444.90 – 1,454.18

24793 votes

Category
industry_software_and_it_services
Evaluated configuration
Grok 4.1
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating

Grok 4.1

1,406.99 rating

Confidence interval: 1,401.46 – 1,412.51

15343 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
Grok 4.1
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating

Grok 4.1

1,399.67 rating

Confidence interval: 1,394.66 – 1,404.69

19510 votes

Category
instruction_following
Evaluated configuration
Grok 4.1
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-10-28 · rating

Grok 4.1

1,397.34 rating

Confidence interval: 1,375.24 – 1,419.44

714 votes

Category
japanese
Evaluated configuration
Grok 4.1
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-10-28 · rating

Grok 4.1

1,406.37 rating

Confidence interval: 1,388.07 – 1,424.67

1146 votes

Category
korean
Evaluated configuration
Grok 4.1
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating

Grok 4.1

1,415.85 rating

Confidence interval: 1,410.89 – 1,420.81

21139 votes

Category
longer_query
Evaluated configuration
Grok 4.1
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating

Grok 4.1

1,416.19 rating

Confidence interval: 1,407.05 – 1,425.33

4354 votes

Category
math
Evaluated configuration
Grok 4.1
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating

Grok 4.1

1,437.45 rating

Confidence interval: 1,431.28 – 1,443.63

12420 votes

Category
multi_turn
Evaluated configuration
Grok 4.1
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating

Grok 4.1

1,421.80 rating

Confidence interval: 1,417.92 – 1,425.69

39559 votes

Category
non_english
Evaluated configuration
Grok 4.1
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating

Grok 4.1

1,435.96 rating

Confidence interval: 1,432.83 – 1,439.08

68599 votes

Category
overall
Evaluated configuration
Grok 4.1
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-10-28 · rating

Grok 4.1

1,451.59 rating

Confidence interval: 1,438.20 – 1,464.98

2023 votes

Category
polish
Evaluated configuration
Grok 4.1
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating

Grok 4.1

1,425.87 rating

Confidence interval: 1,418.76 – 1,432.99

7870 votes

Category
russian
Evaluated configuration
Grok 4.1
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-10-28 · rating

Grok 4.1

1,425.17 rating

Confidence interval: 1,411.31 – 1,439.03

1991 votes

Category
spanish
Evaluated configuration
Grok 4.1
Evaluation type
human preference

Run it locally

Inference · memory estimate

Grok 4.1

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license
Proprietary