GeekRadar / The comparison desk
COMPARE.
AI models
anthropic

Claude Opus 4.1 (20250805)

Model evaluation

Capability & preference

Human preference · Arena

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

Claude Opus 4.1 (20250805) 1418.7 Claude Opus 4.1 (20250805) · 95% interval 1415.7–1421.6 · 77,172 votes · 2026-11-06

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 · 2026-11-06 · rating

Claude Opus 4.1 (20250805)

1,426.93 rating

Confidence interval: 1,418.87 – 1,435.00

5945 votes

Category
chinese
Evaluated configuration
Claude Opus 4.1 (20250805)
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-11-06 · rating

Claude Opus 4.1 (20250805)

1,472.49 rating

Confidence interval: 1,467.15 – 1,477.84

15681 votes

Category
coding
Evaluated configuration
Claude Opus 4.1 (20250805)
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-11-06 · rating

Claude Opus 4.1 (20250805)

1,410.64 rating

Confidence interval: 1,404.42 – 1,416.86

10858 votes

Category
creative_writing
Evaluated configuration
Claude Opus 4.1 (20250805)
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-11-06 · rating

Claude Opus 4.1 (20250805)

1,426.63 rating

Confidence interval: 1,422.52 – 1,430.74

32126 votes

Category
english
Evaluated configuration
Claude Opus 4.1 (20250805)
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-11-06 · rating

Claude Opus 4.1 (20250805)

1,405.52 rating

Confidence interval: 1,401.46 – 1,409.58

55535 votes

Category
exclude_ties
Evaluated configuration
Claude Opus 4.1 (20250805)
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-11-06 · rating

Claude Opus 4.1 (20250805)

1,425.37 rating

Confidence interval: 1,416.14 – 1,434.60

4234 votes

Category
expert
Evaluated configuration
Claude Opus 4.1 (20250805)
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-11-06 · rating

Claude Opus 4.1 (20250805)

1,428.03 rating

Confidence interval: 1,411.43 – 1,444.63

1417 votes

Category
french
Evaluated configuration
Claude Opus 4.1 (20250805)
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-11-06 · rating

Claude Opus 4.1 (20250805)

1,405.22 rating

Confidence interval: 1,389.76 – 1,420.67

1564 votes

Category
german
Evaluated configuration
Claude Opus 4.1 (20250805)
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-11-06 · rating

Claude Opus 4.1 (20250805)

1,442.10 rating

Confidence interval: 1,438.24 – 1,445.96

39417 votes

Category
hard_prompts
Evaluated configuration
Claude Opus 4.1 (20250805)
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-11-06 · rating

Claude Opus 4.1 (20250805)

1,448.06 rating

Confidence interval: 1,442.82 – 1,453.29

16428 votes

Category
hard_prompts_english
Evaluated configuration
Claude Opus 4.1 (20250805)
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-11-06 · rating

Claude Opus 4.1 (20250805)

1,405.55 rating

Confidence interval: 1,399.96 – 1,411.14

14063 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
Claude Opus 4.1 (20250805)
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-11-06 · rating

Claude Opus 4.1 (20250805)

1,398.57 rating

Confidence interval: 1,393.03 – 1,404.11

14219 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
Claude Opus 4.1 (20250805)
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-11-06 · rating

Claude Opus 4.1 (20250805)

1,417.47 rating

Confidence interval: 1,409.06 – 1,425.87

5333 votes

Category
industry_legal_and_government
Evaluated configuration
Claude Opus 4.1 (20250805)
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-11-06 · rating

Claude Opus 4.1 (20250805)

1,416.77 rating

Confidence interval: 1,410.94 – 1,422.61

12261 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
Claude Opus 4.1 (20250805)
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-11-06 · rating

Claude Opus 4.1 (20250805)

1,426.03 rating

Confidence interval: 1,416.65 – 1,435.42

3899 votes

Category
industry_mathematical
Evaluated configuration
Claude Opus 4.1 (20250805)
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-11-06 · rating

Claude Opus 4.1 (20250805)

1,412.88 rating

Confidence interval: 1,403.53 – 1,422.24

4427 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
Claude Opus 4.1 (20250805)
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-11-06 · rating

Claude Opus 4.1 (20250805)

1,451.49 rating

Confidence interval: 1,447.05 – 1,455.94

26032 votes

Category
industry_software_and_it_services
Evaluated configuration
Claude Opus 4.1 (20250805)
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-11-06 · rating

Claude Opus 4.1 (20250805)

1,418.17 rating

Confidence interval: 1,413.01 – 1,423.33

17457 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
Claude Opus 4.1 (20250805)
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-11-06 · rating

Claude Opus 4.1 (20250805)

1,433.67 rating

Confidence interval: 1,428.84 – 1,438.49

20774 votes

Category
instruction_following
Evaluated configuration
Claude Opus 4.1 (20250805)
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-11-06 · rating

Claude Opus 4.1 (20250805)

1,374.48 rating

Confidence interval: 1,356.73 – 1,392.24

1198 votes

Category
japanese
Evaluated configuration
Claude Opus 4.1 (20250805)
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-11-06 · rating

Claude Opus 4.1 (20250805)

1,364.50 rating

Confidence interval: 1,348.93 – 1,380.07

1612 votes

Category
korean
Evaluated configuration
Claude Opus 4.1 (20250805)
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-11-06 · rating

Claude Opus 4.1 (20250805)

1,444.34 rating

Confidence interval: 1,439.30 – 1,449.39

18467 votes

Category
longer_query
Evaluated configuration
Claude Opus 4.1 (20250805)
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-11-06 · rating

Claude Opus 4.1 (20250805)

1,421.75 rating

Confidence interval: 1,413.26 – 1,430.23

4802 votes

Category
math
Evaluated configuration
Claude Opus 4.1 (20250805)
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-11-06 · rating

Claude Opus 4.1 (20250805)

1,443.22 rating

Confidence interval: 1,437.43 – 1,449.01

13107 votes

Category
multi_turn
Evaluated configuration
Claude Opus 4.1 (20250805)
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-11-06 · rating

Claude Opus 4.1 (20250805)

1,405.42 rating

Confidence interval: 1,401.74 – 1,409.10

45008 votes

Category
non_english
Evaluated configuration
Claude Opus 4.1 (20250805)
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-11-06 · rating

Claude Opus 4.1 (20250805)

1,418.66 rating

Confidence interval: 1,415.69 – 1,421.64

77172 votes

Category
overall
Evaluated configuration
Claude Opus 4.1 (20250805)
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-11-06 · rating

Claude Opus 4.1 (20250805)

1,412.93 rating

Confidence interval: 1,402.70 – 1,423.17

3730 votes

Category
polish
Evaluated configuration
Claude Opus 4.1 (20250805)
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-11-06 · rating

Claude Opus 4.1 (20250805)

1,421.50 rating

Confidence interval: 1,414.37 – 1,428.63

7228 votes

Category
russian
Evaluated configuration
Claude Opus 4.1 (20250805)
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-11-06 · rating

Claude Opus 4.1 (20250805)

1,448.53 rating

Confidence interval: 1,435.24 – 1,461.83

2300 votes

Category
spanish
Evaluated configuration
Claude Opus 4.1 (20250805)
Evaluation type
human preference

Run it locally

Inference · memory estimate

Claude Opus 4.1 (20250805)

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license
Proprietary