GeekRadar / The comparison desk
COMPARE.
AI models
xai

Grok 2 mini (2024-08-13)

Model evaluation

Capability & preference

Human preference · Arena

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

Grok 2 mini (2024-08-13) 1280.7 Grok 2 mini (2024-08-13) · 95% interval 1277.0–1284.4 · 52,567 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 2 mini (2024-08-13)

1,262.37 rating

Confidence interval: 1,252.38 – 1,272.36

4510 votes

Category
chinese
Evaluated configuration
Grok 2 mini (2024-08-13)
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating

Grok 2 mini (2024-08-13)

1,268.28 rating

Confidence interval: 1,261.14 – 1,275.43

8652 votes

Category
coding
Evaluated configuration
Grok 2 mini (2024-08-13)
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating

Grok 2 mini (2024-08-13)

1,241.24 rating

Confidence interval: 1,233.56 – 1,248.93

7924 votes

Category
creative_writing
Evaluated configuration
Grok 2 mini (2024-08-13)
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating

Grok 2 mini (2024-08-13)

1,298.01 rating

Confidence interval: 1,293.19 – 1,302.84

28429 votes

Category
english
Evaluated configuration
Grok 2 mini (2024-08-13)
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating

Grok 2 mini (2024-08-13)

1,208.23 rating

Confidence interval: 1,202.48 – 1,213.97

33168 votes

Category
exclude_ties
Evaluated configuration
Grok 2 mini (2024-08-13)
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-28 · rating

Grok 2 mini (2024-08-13)

1,237.59 rating

Confidence interval: 1,225.91 – 1,249.26

2759 votes

Category
expert
Evaluated configuration
Grok 2 mini (2024-08-13)
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating

Grok 2 mini (2024-08-13)

1,286.54 rating

Confidence interval: 1,257.69 – 1,315.39

471 votes

Category
french
Evaluated configuration
Grok 2 mini (2024-08-13)
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating

Grok 2 mini (2024-08-13)

1,272.80 rating

Confidence interval: 1,255.54 – 1,290.06

1298 votes

Category
german
Evaluated configuration
Grok 2 mini (2024-08-13)
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating

Grok 2 mini (2024-08-13)

1,254.78 rating

Confidence interval: 1,248.94 – 1,260.62

14208 votes

Category
hard_prompts
Evaluated configuration
Grok 2 mini (2024-08-13)
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating

Grok 2 mini (2024-08-13)

1,267.49 rating

Confidence interval: 1,260.41 – 1,274.58

8664 votes

Category
hard_prompts_english
Evaluated configuration
Grok 2 mini (2024-08-13)
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating

Grok 2 mini (2024-08-13)

1,253.69 rating

Confidence interval: 1,245.27 – 1,262.11

6124 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
Grok 2 mini (2024-08-13)
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating

Grok 2 mini (2024-08-13)

1,232.84 rating

Confidence interval: 1,225.58 – 1,240.11

8614 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
Grok 2 mini (2024-08-13)
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating

Grok 2 mini (2024-08-13)

1,292.41 rating

Confidence interval: 1,280.52 – 1,304.30

3012 votes

Category
industry_legal_and_government
Evaluated configuration
Grok 2 mini (2024-08-13)
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating

Grok 2 mini (2024-08-13)

1,299.59 rating

Confidence interval: 1,292.16 – 1,307.02

8788 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
Grok 2 mini (2024-08-13)
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating

Grok 2 mini (2024-08-13)

1,272.62 rating

Confidence interval: 1,264.51 – 1,280.73

6253 votes

Category
industry_mathematical
Evaluated configuration
Grok 2 mini (2024-08-13)
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating

Grok 2 mini (2024-08-13)

1,297.72 rating

Confidence interval: 1,284.83 – 1,310.61

2609 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
Grok 2 mini (2024-08-13)
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating

Grok 2 mini (2024-08-13)

1,277.31 rating

Confidence interval: 1,271.17 – 1,283.45

13865 votes

Category
industry_software_and_it_services
Evaluated configuration
Grok 2 mini (2024-08-13)
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating

Grok 2 mini (2024-08-13)

1,262.17 rating

Confidence interval: 1,255.97 – 1,268.37

14508 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
Grok 2 mini (2024-08-13)
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating

Grok 2 mini (2024-08-13)

1,244.58 rating

Confidence interval: 1,239.32 – 1,249.85

21131 votes

Category
instruction_following
Evaluated configuration
Grok 2 mini (2024-08-13)
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-10-28 · rating

Grok 2 mini (2024-08-13)

1,212.99 rating

Confidence interval: 1,194.99 – 1,230.98

1225 votes

Category
japanese
Evaluated configuration
Grok 2 mini (2024-08-13)
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-10-28 · rating

Grok 2 mini (2024-08-13)

1,194.80 rating

Confidence interval: 1,171.33 – 1,218.28

852 votes

Category
korean
Evaluated configuration
Grok 2 mini (2024-08-13)
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating

Grok 2 mini (2024-08-13)

1,266.07 rating

Confidence interval: 1,258.40 – 1,273.74

7048 votes

Category
longer_query
Evaluated configuration
Grok 2 mini (2024-08-13)
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating

Grok 2 mini (2024-08-13)

1,265.12 rating

Confidence interval: 1,257.44 – 1,272.81

7261 votes

Category
math
Evaluated configuration
Grok 2 mini (2024-08-13)
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating

Grok 2 mini (2024-08-13)

1,265.37 rating

Confidence interval: 1,257.98 – 1,272.77

9399 votes

Category
multi_turn
Evaluated configuration
Grok 2 mini (2024-08-13)
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating

Grok 2 mini (2024-08-13)

1,256.89 rating

Confidence interval: 1,251.90 – 1,261.88

24138 votes

Category
non_english
Evaluated configuration
Grok 2 mini (2024-08-13)
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating

Grok 2 mini (2024-08-13)

1,280.67 rating

Confidence interval: 1,276.97 – 1,284.37

52567 votes

Category
overall
Evaluated configuration
Grok 2 mini (2024-08-13)
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating

Grok 2 mini (2024-08-13)

1,261.00 rating

Confidence interval: 1,253.05 – 1,268.96

7193 votes

Category
russian
Evaluated configuration
Grok 2 mini (2024-08-13)
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-10-28 · rating

Grok 2 mini (2024-08-13)

1,278.57 rating

Confidence interval: 1,253.28 – 1,303.86

575 votes

Category
spanish
Evaluated configuration
Grok 2 mini (2024-08-13)
Evaluation type
human preference

Run it locally

Inference · memory estimate

Grok 2 mini (2024-08-13)

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license
Proprietary