GeekRadar / The comparison desk

COMPARE.

AI models

xai

Grok 4.20 Beta (Reasoning, 0309)

Model evaluation

Capability & preference

Human preference · Arena

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

Grok 4.20 Beta (Reasoning, 0309) 1451.0 Grok 4.20 Beta (Reasoning, 0309) · 95% interval 1447.3–1454.6 · 66,422 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 4.20 Beta (Reasoning, 0309)

1,480.80 rating

Confidence interval: 1,471.06 – 1,490.55

4234 votes

Oct 28, 2026

Category: chinese
Evaluated configuration: Grok 4.20 Beta (Reasoning, 0309)
Evaluation type: human preference

Arena text preference / codinghuman preference · 2026-10-28 · rating

Grok 4.20 Beta (Reasoning, 0309)

1,458.65 rating

Confidence interval: 1,452.94 – 1,464.37

18368 votes

Oct 28, 2026

Category: coding
Evaluated configuration: Grok 4.20 Beta (Reasoning, 0309)
Evaluation type: human preference

Arena text preference / creative_writinghuman preference · 2026-10-28 · rating

Grok 4.20 Beta (Reasoning, 0309)

1,431.83 rating

Confidence interval: 1,425.12 – 1,438.55

11423 votes

Oct 28, 2026

Category: creative_writing
Evaluated configuration: Grok 4.20 Beta (Reasoning, 0309)
Evaluation type: human preference

Arena text preference / englishhuman preference · 2026-10-28 · rating

Grok 4.20 Beta (Reasoning, 0309)

1,457.27 rating

Confidence interval: 1,452.43 – 1,462.10

30431 votes

Oct 28, 2026

Category: english
Evaluated configuration: Grok 4.20 Beta (Reasoning, 0309)
Evaluation type: human preference

Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating

Grok 4.20 Beta (Reasoning, 0309)

1,449.68 rating

Confidence interval: 1,444.92 – 1,454.43

50682 votes

Oct 28, 2026

Category: exclude_ties
Evaluated configuration: Grok 4.20 Beta (Reasoning, 0309)
Evaluation type: human preference

Arena text preference / experthuman preference · 2026-10-28 · rating

Grok 4.20 Beta (Reasoning, 0309)

1,438.93 rating

Confidence interval: 1,430.88 – 1,446.97

6694 votes

Oct 28, 2026

Category: expert
Evaluated configuration: Grok 4.20 Beta (Reasoning, 0309)
Evaluation type: human preference

Arena text preference / frenchhuman preference · 2026-10-28 · rating

Grok 4.20 Beta (Reasoning, 0309)

1,476.20 rating

Confidence interval: 1,461.96 – 1,490.45

2216 votes

Oct 28, 2026

Category: french
Evaluated configuration: Grok 4.20 Beta (Reasoning, 0309)
Evaluation type: human preference

Arena text preference / germanhuman preference · 2026-10-28 · rating

Grok 4.20 Beta (Reasoning, 0309)

1,440.56 rating

Confidence interval: 1,421.62 – 1,459.51

1051 votes

Oct 28, 2026

Category: german
Evaluated configuration: Grok 4.20 Beta (Reasoning, 0309)
Evaluation type: human preference

Arena text preference / hard_promptshuman preference · 2026-10-28 · rating

Grok 4.20 Beta (Reasoning, 0309)

1,451.50 rating

Confidence interval: 1,447.11 – 1,455.90

43501 votes

Oct 28, 2026

Category: hard_prompts
Evaluated configuration: Grok 4.20 Beta (Reasoning, 0309)
Evaluation type: human preference

Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating

Grok 4.20 Beta (Reasoning, 0309)

1,454.71 rating

Confidence interval: 1,449.19 – 1,460.23

20639 votes

Oct 28, 2026

Category: hard_prompts_english
Evaluated configuration: Grok 4.20 Beta (Reasoning, 0309)
Evaluation type: human preference

Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating

Grok 4.20 Beta (Reasoning, 0309)

1,431.89 rating

Confidence interval: 1,425.70 – 1,438.09

13361 votes

Oct 28, 2026

Category: industry_business_and_management_and_financial_operations
Evaluated configuration: Grok 4.20 Beta (Reasoning, 0309)
Evaluation type: human preference

Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating

Grok 4.20 Beta (Reasoning, 0309)

1,425.94 rating

Confidence interval: 1,419.77 – 1,432.11

14778 votes

Oct 28, 2026

Category: industry_entertainment_and_sports_and_media
Evaluated configuration: Grok 4.20 Beta (Reasoning, 0309)
Evaluation type: human preference

Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating

Grok 4.20 Beta (Reasoning, 0309)

1,453.82 rating

Confidence interval: 1,444.95 – 1,462.68

5327 votes

Oct 28, 2026

Category: industry_legal_and_government
Evaluated configuration: Grok 4.20 Beta (Reasoning, 0309)
Evaluation type: human preference

Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating

Grok 4.20 Beta (Reasoning, 0309)

1,462.80 rating

Confidence interval: 1,456.18 – 1,469.42

10867 votes

Oct 28, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: Grok 4.20 Beta (Reasoning, 0309)
Evaluation type: human preference

Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating

Grok 4.20 Beta (Reasoning, 0309)

1,446.29 rating

Confidence interval: 1,435.87 – 1,456.70

3643 votes

Oct 28, 2026

Category: industry_mathematical
Evaluated configuration: Grok 4.20 Beta (Reasoning, 0309)
Evaluation type: human preference

Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating

Grok 4.20 Beta (Reasoning, 0309)

1,453.86 rating

Confidence interval: 1,444.72 – 1,462.99

4952 votes

Oct 28, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: Grok 4.20 Beta (Reasoning, 0309)
Evaluation type: human preference

Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating

Grok 4.20 Beta (Reasoning, 0309)

1,461.28 rating

Confidence interval: 1,456.21 – 1,466.35

26051 votes

Oct 28, 2026

Category: industry_software_and_it_services
Evaluated configuration: Grok 4.20 Beta (Reasoning, 0309)
Evaluation type: human preference

Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating

Grok 4.20 Beta (Reasoning, 0309)

1,433.68 rating

Confidence interval: 1,427.82 – 1,439.54

16602 votes

Oct 28, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: Grok 4.20 Beta (Reasoning, 0309)
Evaluation type: human preference

Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating

Grok 4.20 Beta (Reasoning, 0309)

1,420.54 rating

Confidence interval: 1,415.24 – 1,425.85

22630 votes

Oct 28, 2026

Category: instruction_following
Evaluated configuration: Grok 4.20 Beta (Reasoning, 0309)
Evaluation type: human preference

Arena text preference / japanesehuman preference · 2026-10-28 · rating

Grok 4.20 Beta (Reasoning, 0309)

1,414.31 rating

Confidence interval: 1,390.86 – 1,437.75

706 votes

Oct 28, 2026

Category: japanese
Evaluated configuration: Grok 4.20 Beta (Reasoning, 0309)
Evaluation type: human preference

Arena text preference / koreanhuman preference · 2026-10-28 · rating

Grok 4.20 Beta (Reasoning, 0309)

1,415.31 rating

Confidence interval: 1,395.80 – 1,434.81

1067 votes

Oct 28, 2026

Category: korean
Evaluated configuration: Grok 4.20 Beta (Reasoning, 0309)
Evaluation type: human preference

Arena text preference / longer_queryhuman preference · 2026-10-28 · rating

Grok 4.20 Beta (Reasoning, 0309)

1,436.66 rating

Confidence interval: 1,431.53 – 1,441.78

29106 votes

Oct 28, 2026

Category: longer_query
Evaluated configuration: Grok 4.20 Beta (Reasoning, 0309)
Evaluation type: human preference

Arena text preference / mathhuman preference · 2026-10-28 · rating

Grok 4.20 Beta (Reasoning, 0309)

1,455.22 rating

Confidence interval: 1,444.82 – 1,465.62

3542 votes

Oct 28, 2026

Category: math
Evaluated configuration: Grok 4.20 Beta (Reasoning, 0309)
Evaluation type: human preference

Arena text preference / multi_turnhuman preference · 2026-10-28 · rating

Grok 4.20 Beta (Reasoning, 0309)

1,455.72 rating

Confidence interval: 1,449.21 – 1,462.24

12122 votes

Oct 28, 2026

Category: multi_turn
Evaluated configuration: Grok 4.20 Beta (Reasoning, 0309)
Evaluation type: human preference

Arena text preference / non_englishhuman preference · 2026-10-28 · rating

Grok 4.20 Beta (Reasoning, 0309)

1,440.86 rating

Confidence interval: 1,436.33 – 1,445.38

35991 votes

Oct 28, 2026

Category: non_english
Evaluated configuration: Grok 4.20 Beta (Reasoning, 0309)
Evaluation type: human preference

Arena text preference / overallhuman preference · 2026-10-28 · rating

Grok 4.20 Beta (Reasoning, 0309)

1,450.98 rating

Confidence interval: 1,447.33 – 1,454.64

66422 votes

Oct 28, 2026

Category: overall
Evaluated configuration: Grok 4.20 Beta (Reasoning, 0309)
Evaluation type: human preference

Arena text preference / polishhuman preference · 2026-10-28 · rating

Grok 4.20 Beta (Reasoning, 0309)

1,451.44 rating

Confidence interval: 1,434.68 – 1,468.20

1254 votes

Oct 28, 2026

Category: polish
Evaluated configuration: Grok 4.20 Beta (Reasoning, 0309)
Evaluation type: human preference

Arena text preference / russianhuman preference · 2026-10-28 · rating

Grok 4.20 Beta (Reasoning, 0309)

1,457.58 rating

Confidence interval: 1,449.96 – 1,465.20

7432 votes

Oct 28, 2026

Category: russian
Evaluated configuration: Grok 4.20 Beta (Reasoning, 0309)
Evaluation type: human preference

Arena text preference / spanishhuman preference · 2026-10-28 · rating

Grok 4.20 Beta (Reasoning, 0309)

1,442.98 rating

Confidence interval: 1,429.02 – 1,456.94

2062 votes

Oct 28, 2026

Category: spanish
Evaluated configuration: Grok 4.20 Beta (Reasoning, 0309)
Evaluation type: human preference

Run it locally

Inference · memory estimate

Grok 4.20 Beta (Reasoning, 0309)

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license: Proprietary