GeekRadar / The comparison desk
COMPARE.
AI models
xai

grok-3-mini-beta

Model evaluation

Capability & preference

Human preference · Arena

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

grok-3-mini-beta 1364.3 grok-3-mini-beta · 95% interval 1359.2–1369.4 · 20,931 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-3-mini-beta

1,377.13 rating

Confidence interval: 1,360.81 – 1,393.46

1302 votes

Category
chinese
Evaluated configuration
grok-3-mini-beta
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating

grok-3-mini-beta

1,366.44 rating

Confidence interval: 1,357.26 – 1,375.62

4094 votes

Category
coding
Evaluated configuration
grok-3-mini-beta
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating

grok-3-mini-beta

1,341.58 rating

Confidence interval: 1,330.05 – 1,353.11

2574 votes

Category
creative_writing
Evaluated configuration
grok-3-mini-beta
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating

grok-3-mini-beta

1,376.06 rating

Confidence interval: 1,369.48 – 1,382.65

9863 votes

Category
english
Evaluated configuration
grok-3-mini-beta
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating

grok-3-mini-beta

1,329.30 rating

Confidence interval: 1,322.32 – 1,336.28

14728 votes

Category
exclude_ties
Evaluated configuration
grok-3-mini-beta
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-15 · rating

grok-3-mini-beta

1,365.89 rating

Confidence interval: 1,348.60 – 1,383.18

1138 votes

Category
expert
Evaluated configuration
grok-3-mini-beta
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating

grok-3-mini-beta

1,356.84 rating

Confidence interval: 1,319.92 – 1,393.75

275 votes

Category
french
Evaluated configuration
grok-3-mini-beta
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating

grok-3-mini-beta

1,347.32 rating

Confidence interval: 1,322.32 – 1,372.32

538 votes

Category
german
Evaluated configuration
grok-3-mini-beta
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating

grok-3-mini-beta

1,363.62 rating

Confidence interval: 1,356.96 – 1,370.28

9239 votes

Category
hard_prompts
Evaluated configuration
grok-3-mini-beta
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating

grok-3-mini-beta

1,375.46 rating

Confidence interval: 1,366.59 – 1,384.33

4490 votes

Category
hard_prompts_english
Evaluated configuration
grok-3-mini-beta
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating

grok-3-mini-beta

1,347.20 rating

Confidence interval: 1,336.91 – 1,357.49

3336 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
grok-3-mini-beta
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating

grok-3-mini-beta

1,331.71 rating

Confidence interval: 1,322.01 – 1,341.41

3623 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
grok-3-mini-beta
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating

grok-3-mini-beta

1,371.57 rating

Confidence interval: 1,355.63 – 1,387.51

1404 votes

Category
industry_legal_and_government
Evaluated configuration
grok-3-mini-beta
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating

grok-3-mini-beta

1,374.12 rating

Confidence interval: 1,364.19 – 1,384.06

3663 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
grok-3-mini-beta
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating

grok-3-mini-beta

1,359.85 rating

Confidence interval: 1,344.96 – 1,374.73

1413 votes

Category
industry_mathematical
Evaluated configuration
grok-3-mini-beta
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating

grok-3-mini-beta

1,366.01 rating

Confidence interval: 1,349.67 – 1,382.36

1369 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
grok-3-mini-beta
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating

grok-3-mini-beta

1,373.20 rating

Confidence interval: 1,365.73 – 1,380.67

6889 votes

Category
industry_software_and_it_services
Evaluated configuration
grok-3-mini-beta
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating

grok-3-mini-beta

1,344.92 rating

Confidence interval: 1,336.09 – 1,353.76

4563 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
grok-3-mini-beta
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating

grok-3-mini-beta

1,345.90 rating

Confidence interval: 1,337.80 – 1,354.00

5434 votes

Category
instruction_following
Evaluated configuration
grok-3-mini-beta
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating

grok-3-mini-beta

1,341.96 rating

Confidence interval: 1,317.28 – 1,366.63

600 votes

Category
japanese
Evaluated configuration
grok-3-mini-beta
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating

grok-3-mini-beta

1,305.98 rating

Confidence interval: 1,276.03 – 1,335.92

396 votes

Category
korean
Evaluated configuration
grok-3-mini-beta
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating

grok-3-mini-beta

1,357.21 rating

Confidence interval: 1,347.94 – 1,366.49

4036 votes

Category
longer_query
Evaluated configuration
grok-3-mini-beta
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating

grok-3-mini-beta

1,372.34 rating

Confidence interval: 1,358.09 – 1,386.58

1513 votes

Category
math
Evaluated configuration
grok-3-mini-beta
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating

grok-3-mini-beta

1,350.94 rating

Confidence interval: 1,340.79 – 1,361.09

3390 votes

Category
multi_turn
Evaluated configuration
grok-3-mini-beta
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating

grok-3-mini-beta

1,348.38 rating

Confidence interval: 1,342.15 – 1,354.61

11060 votes

Category
non_english
Evaluated configuration
grok-3-mini-beta
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating

grok-3-mini-beta

1,364.26 rating

Confidence interval: 1,359.16 – 1,369.36

20931 votes

Category
overall
Evaluated configuration
grok-3-mini-beta
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-10-15 · rating

grok-3-mini-beta

1,352.27 rating

Confidence interval: 1,337.87 – 1,366.67

1800 votes

Category
polish
Evaluated configuration
grok-3-mini-beta
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating

grok-3-mini-beta

1,353.44 rating

Confidence interval: 1,339.41 – 1,367.46

1629 votes

Category
russian
Evaluated configuration
grok-3-mini-beta
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating

grok-3-mini-beta

1,380.57 rating

Confidence interval: 1,351.25 – 1,409.90

394 votes

Category
spanish
Evaluated configuration
grok-3-mini-beta
Evaluation type
human preference

Run it locally

Inference · memory estimate

grok-3-mini-beta

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license
Proprietary