GeekRadar / The comparison desk
COMPARE.
AI models
xai

grok-4.20-multi-agent-beta-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-multi-agent-beta-0309 1450.3 grok-4.20-multi-agent-beta-0309 · 95% interval 1446.6–1454.0 · 64,946 votes · 2026-10-15

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 · 2026-10-15 · rating

grok-4.20-multi-agent-beta-0309

1,474.80 rating

Confidence interval: 1,465.00 – 1,484.60

4047 votes

Category
chinese
Evaluated configuration
grok-4.20-multi-agent-beta-0309
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating

grok-4.20-multi-agent-beta-0309

1,457.27 rating

Confidence interval: 1,451.57 – 1,462.97

18016 votes

Category
coding
Evaluated configuration
grok-4.20-multi-agent-beta-0309
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating

grok-4.20-multi-agent-beta-0309

1,436.04 rating

Confidence interval: 1,429.30 – 1,442.77

11305 votes

Category
creative_writing
Evaluated configuration
grok-4.20-multi-agent-beta-0309
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating

grok-4.20-multi-agent-beta-0309

1,452.60 rating

Confidence interval: 1,447.73 – 1,457.47

29601 votes

Category
english
Evaluated configuration
grok-4.20-multi-agent-beta-0309
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating

grok-4.20-multi-agent-beta-0309

1,447.72 rating

Confidence interval: 1,442.93 – 1,452.51

49123 votes

Category
exclude_ties
Evaluated configuration
grok-4.20-multi-agent-beta-0309
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-15 · rating

grok-4.20-multi-agent-beta-0309

1,444.84 rating

Confidence interval: 1,436.83 – 1,452.86

6554 votes

Category
expert
Evaluated configuration
grok-4.20-multi-agent-beta-0309
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating

grok-4.20-multi-agent-beta-0309

1,465.98 rating

Confidence interval: 1,451.92 – 1,480.03

2268 votes

Category
french
Evaluated configuration
grok-4.20-multi-agent-beta-0309
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating

grok-4.20-multi-agent-beta-0309

1,456.23 rating

Confidence interval: 1,437.03 – 1,475.43

1058 votes

Category
german
Evaluated configuration
grok-4.20-multi-agent-beta-0309
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating

grok-4.20-multi-agent-beta-0309

1,447.98 rating

Confidence interval: 1,443.56 – 1,452.40

42170 votes

Category
hard_prompts
Evaluated configuration
grok-4.20-multi-agent-beta-0309
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating

grok-4.20-multi-agent-beta-0309

1,446.29 rating

Confidence interval: 1,440.74 – 1,451.84

19980 votes

Category
hard_prompts_english
Evaluated configuration
grok-4.20-multi-agent-beta-0309
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating

grok-4.20-multi-agent-beta-0309

1,422.49 rating

Confidence interval: 1,416.23 – 1,428.75

12900 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
grok-4.20-multi-agent-beta-0309
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating

grok-4.20-multi-agent-beta-0309

1,421.92 rating

Confidence interval: 1,415.72 – 1,428.12

14205 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
grok-4.20-multi-agent-beta-0309
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating

grok-4.20-multi-agent-beta-0309

1,448.56 rating

Confidence interval: 1,439.72 – 1,457.40

5186 votes

Category
industry_legal_and_government
Evaluated configuration
grok-4.20-multi-agent-beta-0309
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating

grok-4.20-multi-agent-beta-0309

1,454.82 rating

Confidence interval: 1,448.22 – 1,461.42

10689 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
grok-4.20-multi-agent-beta-0309
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating

grok-4.20-multi-agent-beta-0309

1,440.98 rating

Confidence interval: 1,430.52 – 1,451.43

3549 votes

Category
industry_mathematical
Evaluated configuration
grok-4.20-multi-agent-beta-0309
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating

grok-4.20-multi-agent-beta-0309

1,452.20 rating

Confidence interval: 1,443.02 – 1,461.38

4843 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
grok-4.20-multi-agent-beta-0309
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating

grok-4.20-multi-agent-beta-0309

1,461.02 rating

Confidence interval: 1,455.95 – 1,466.10

25574 votes

Category
industry_software_and_it_services
Evaluated configuration
grok-4.20-multi-agent-beta-0309
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating

grok-4.20-multi-agent-beta-0309

1,430.45 rating

Confidence interval: 1,424.59 – 1,436.31

16167 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
grok-4.20-multi-agent-beta-0309
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating

grok-4.20-multi-agent-beta-0309

1,419.88 rating

Confidence interval: 1,414.57 – 1,425.18

21965 votes

Category
instruction_following
Evaluated configuration
grok-4.20-multi-agent-beta-0309
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating

grok-4.20-multi-agent-beta-0309

1,405.07 rating

Confidence interval: 1,380.36 – 1,429.78

624 votes

Category
japanese
Evaluated configuration
grok-4.20-multi-agent-beta-0309
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating

grok-4.20-multi-agent-beta-0309

1,414.85 rating

Confidence interval: 1,395.52 – 1,434.17

1049 votes

Category
korean
Evaluated configuration
grok-4.20-multi-agent-beta-0309
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating

grok-4.20-multi-agent-beta-0309

1,430.44 rating

Confidence interval: 1,425.27 – 1,435.60

27975 votes

Category
longer_query
Evaluated configuration
grok-4.20-multi-agent-beta-0309
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating

grok-4.20-multi-agent-beta-0309

1,440.98 rating

Confidence interval: 1,430.51 – 1,451.45

3389 votes

Category
math
Evaluated configuration
grok-4.20-multi-agent-beta-0309
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating

grok-4.20-multi-agent-beta-0309

1,451.87 rating

Confidence interval: 1,445.22 – 1,458.53

10626 votes

Category
multi_turn
Evaluated configuration
grok-4.20-multi-agent-beta-0309
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating

grok-4.20-multi-agent-beta-0309

1,439.80 rating

Confidence interval: 1,435.29 – 1,444.32

35344 votes

Category
non_english
Evaluated configuration
grok-4.20-multi-agent-beta-0309
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating

grok-4.20-multi-agent-beta-0309

1,450.27 rating

Confidence interval: 1,446.59 – 1,453.95

64946 votes

Category
overall
Evaluated configuration
grok-4.20-multi-agent-beta-0309
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-10-15 · rating

grok-4.20-multi-agent-beta-0309

1,453.35 rating

Confidence interval: 1,437.13 – 1,469.56

1315 votes

Category
polish
Evaluated configuration
grok-4.20-multi-agent-beta-0309
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating

grok-4.20-multi-agent-beta-0309

1,456.82 rating

Confidence interval: 1,449.13 – 1,464.52

7160 votes

Category
russian
Evaluated configuration
grok-4.20-multi-agent-beta-0309
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating

grok-4.20-multi-agent-beta-0309

1,447.35 rating

Confidence interval: 1,433.09 – 1,461.60

1997 votes

Category
spanish
Evaluated configuration
grok-4.20-multi-agent-beta-0309
Evaluation type
human preference

Run it locally

Inference · memory estimate

grok-4.20-multi-agent-beta-0309

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license
Proprietary