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 1364.2 Grok 3 Mini Beta · 95% interval 1359.1–1369.3 · 20,930 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 3 Mini Beta

1,376.99 rating

Confidence interval: 1,360.66 – 1,393.32

1302 votes

Category
chinese
Evaluated configuration
Grok 3 Mini Beta
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating

Grok 3 Mini Beta

1,366.34 rating

Confidence interval: 1,357.16 – 1,375.52

4094 votes

Category
coding
Evaluated configuration
Grok 3 Mini Beta
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating

Grok 3 Mini Beta

1,341.24 rating

Confidence interval: 1,329.71 – 1,352.77

2574 votes

Category
creative_writing
Evaluated configuration
Grok 3 Mini Beta
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating

Grok 3 Mini Beta

1,376.12 rating

Confidence interval: 1,369.53 – 1,382.70

9862 votes

Category
english
Evaluated configuration
Grok 3 Mini Beta
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating

Grok 3 Mini Beta

1,329.26 rating

Confidence interval: 1,322.27 – 1,336.24

14727 votes

Category
exclude_ties
Evaluated configuration
Grok 3 Mini Beta
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-28 · rating

Grok 3 Mini Beta

1,365.86 rating

Confidence interval: 1,348.57 – 1,383.15

1138 votes

Category
expert
Evaluated configuration
Grok 3 Mini Beta
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating

Grok 3 Mini Beta

1,357.30 rating

Confidence interval: 1,320.40 – 1,394.21

275 votes

Category
french
Evaluated configuration
Grok 3 Mini Beta
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating

Grok 3 Mini Beta

1,347.71 rating

Confidence interval: 1,322.68 – 1,372.74

537 votes

Category
german
Evaluated configuration
Grok 3 Mini Beta
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating

Grok 3 Mini Beta

1,363.58 rating

Confidence interval: 1,356.92 – 1,370.24

9237 votes

Category
hard_prompts
Evaluated configuration
Grok 3 Mini Beta
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating

Grok 3 Mini Beta

1,375.56 rating

Confidence interval: 1,366.68 – 1,384.43

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 · 2026-10-28 · rating

Grok 3 Mini Beta

1,347.13 rating

Confidence interval: 1,336.84 – 1,357.42

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 · 2026-10-28 · rating

Grok 3 Mini Beta

1,331.49 rating

Confidence interval: 1,321.80 – 1,341.19

3621 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 · 2026-10-28 · rating

Grok 3 Mini Beta

1,371.82 rating

Confidence interval: 1,355.87 – 1,387.76

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 · 2026-10-28 · rating

Grok 3 Mini Beta

1,374.04 rating

Confidence interval: 1,364.10 – 1,383.97

3664 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 · 2026-10-28 · rating

Grok 3 Mini Beta

1,359.82 rating

Confidence interval: 1,344.93 – 1,374.71

1413 votes

Category
industry_mathematical
Evaluated configuration
Grok 3 Mini Beta
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating

Grok 3 Mini Beta

1,365.53 rating

Confidence interval: 1,349.19 – 1,381.88

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 · 2026-10-28 · rating

Grok 3 Mini Beta

1,373.09 rating

Confidence interval: 1,365.63 – 1,380.56

6888 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 · 2026-10-28 · rating

Grok 3 Mini Beta

1,344.75 rating

Confidence interval: 1,335.92 – 1,353.58

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 · 2026-10-28 · rating

Grok 3 Mini Beta

1,345.87 rating

Confidence interval: 1,337.77 – 1,353.97

5433 votes

Category
instruction_following
Evaluated configuration
Grok 3 Mini Beta
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-10-28 · rating

Grok 3 Mini Beta

1,341.74 rating

Confidence interval: 1,317.03 – 1,366.45

599 votes

Category
japanese
Evaluated configuration
Grok 3 Mini Beta
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-10-28 · rating

Grok 3 Mini Beta

1,304.98 rating

Confidence interval: 1,275.05 – 1,334.91

397 votes

Category
korean
Evaluated configuration
Grok 3 Mini Beta
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating

Grok 3 Mini Beta

1,356.98 rating

Confidence interval: 1,347.70 – 1,366.25

4036 votes

Category
longer_query
Evaluated configuration
Grok 3 Mini Beta
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating

Grok 3 Mini Beta

1,372.32 rating

Confidence interval: 1,358.07 – 1,386.56

1513 votes

Category
math
Evaluated configuration
Grok 3 Mini Beta
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating

Grok 3 Mini Beta

1,350.97 rating

Confidence interval: 1,340.82 – 1,361.12

3389 votes

Category
multi_turn
Evaluated configuration
Grok 3 Mini Beta
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating

Grok 3 Mini Beta

1,348.26 rating

Confidence interval: 1,342.03 – 1,354.50

11060 votes

Category
non_english
Evaluated configuration
Grok 3 Mini Beta
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating

Grok 3 Mini Beta

1,364.24 rating

Confidence interval: 1,359.14 – 1,369.34

20930 votes

Category
overall
Evaluated configuration
Grok 3 Mini Beta
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-10-28 · rating

Grok 3 Mini Beta

1,352.07 rating

Confidence interval: 1,337.68 – 1,366.47

1800 votes

Category
polish
Evaluated configuration
Grok 3 Mini Beta
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating

Grok 3 Mini Beta

1,353.18 rating

Confidence interval: 1,339.17 – 1,367.20

1630 votes

Category
russian
Evaluated configuration
Grok 3 Mini Beta
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-10-28 · rating

Grok 3 Mini Beta

1,380.66 rating

Confidence interval: 1,351.34 – 1,409.98

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