GeekRadar / The comparison desk
COMPARE.
AI models
anthropic

Claude Opus 4.1 (Thinking 16K, 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 (Thinking 16K, 20250805) 1419.3 Claude Opus 4.1 (Thinking 16K, 20250805) · 95% interval 1415.8–1422.7 · 49,374 votes · 2026-11-09

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 · 2026-11-09 · rating

Claude Opus 4.1 (Thinking 16K, 20250805)

1,425.02 rating

Confidence interval: 1,415.21 – 1,434.83

3843 votes

Category
chinese
Evaluated configuration
Claude Opus 4.1 (Thinking 16K, 20250805)
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-11-09 · rating

Claude Opus 4.1 (Thinking 16K, 20250805)

1,478.81 rating

Confidence interval: 1,472.37 – 1,485.24

9886 votes

Category
coding
Evaluated configuration
Claude Opus 4.1 (Thinking 16K, 20250805)
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-11-09 · rating

Claude Opus 4.1 (Thinking 16K, 20250805)

1,411.86 rating

Confidence interval: 1,404.19 – 1,419.53

6817 votes

Category
creative_writing
Evaluated configuration
Claude Opus 4.1 (Thinking 16K, 20250805)
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-11-09 · rating

Claude Opus 4.1 (Thinking 16K, 20250805)

1,432.75 rating

Confidence interval: 1,427.96 – 1,437.54

20830 votes

Category
english
Evaluated configuration
Claude Opus 4.1 (Thinking 16K, 20250805)
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-11-09 · rating

Claude Opus 4.1 (Thinking 16K, 20250805)

1,407.02 rating

Confidence interval: 1,402.29 – 1,411.74

35499 votes

Category
exclude_ties
Evaluated configuration
Claude Opus 4.1 (Thinking 16K, 20250805)
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-11-09 · rating

Claude Opus 4.1 (Thinking 16K, 20250805)

1,439.16 rating

Confidence interval: 1,427.37 – 1,450.96

2524 votes

Category
expert
Evaluated configuration
Claude Opus 4.1 (Thinking 16K, 20250805)
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-11-09 · rating

Claude Opus 4.1 (Thinking 16K, 20250805)

1,432.53 rating

Confidence interval: 1,411.47 – 1,453.60

851 votes

Category
french
Evaluated configuration
Claude Opus 4.1 (Thinking 16K, 20250805)
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-11-09 · rating

Claude Opus 4.1 (Thinking 16K, 20250805)

1,413.01 rating

Confidence interval: 1,394.27 – 1,431.75

1047 votes

Category
german
Evaluated configuration
Claude Opus 4.1 (Thinking 16K, 20250805)
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-11-09 · rating

Claude Opus 4.1 (Thinking 16K, 20250805)

1,442.32 rating

Confidence interval: 1,437.78 – 1,446.86

24857 votes

Category
hard_prompts
Evaluated configuration
Claude Opus 4.1 (Thinking 16K, 20250805)
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-11-09 · rating

Claude Opus 4.1 (Thinking 16K, 20250805)

1,450.98 rating

Confidence interval: 1,444.82 – 1,457.14

10681 votes

Category
hard_prompts_english
Evaluated configuration
Claude Opus 4.1 (Thinking 16K, 20250805)
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-11-09 · rating

Claude Opus 4.1 (Thinking 16K, 20250805)

1,404.85 rating

Confidence interval: 1,398.25 – 1,411.45

9076 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
Claude Opus 4.1 (Thinking 16K, 20250805)
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-11-09 · rating

Claude Opus 4.1 (Thinking 16K, 20250805)

1,396.83 rating

Confidence interval: 1,390.21 – 1,403.45

9045 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
Claude Opus 4.1 (Thinking 16K, 20250805)
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-11-09 · rating

Claude Opus 4.1 (Thinking 16K, 20250805)

1,420.42 rating

Confidence interval: 1,409.93 – 1,430.91

3204 votes

Category
industry_legal_and_government
Evaluated configuration
Claude Opus 4.1 (Thinking 16K, 20250805)
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-11-09 · rating

Claude Opus 4.1 (Thinking 16K, 20250805)

1,421.88 rating

Confidence interval: 1,414.87 – 1,428.89

7906 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
Claude Opus 4.1 (Thinking 16K, 20250805)
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-11-09 · rating

Claude Opus 4.1 (Thinking 16K, 20250805)

1,433.63 rating

Confidence interval: 1,422.01 – 1,445.25

2457 votes

Category
industry_mathematical
Evaluated configuration
Claude Opus 4.1 (Thinking 16K, 20250805)
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-11-09 · rating

Claude Opus 4.1 (Thinking 16K, 20250805)

1,414.98 rating

Confidence interval: 1,403.40 – 1,426.56

2687 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
Claude Opus 4.1 (Thinking 16K, 20250805)
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-11-09 · rating

Claude Opus 4.1 (Thinking 16K, 20250805)

1,456.26 rating

Confidence interval: 1,451.03 – 1,461.49

16686 votes

Category
industry_software_and_it_services
Evaluated configuration
Claude Opus 4.1 (Thinking 16K, 20250805)
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-11-09 · rating

Claude Opus 4.1 (Thinking 16K, 20250805)

1,417.77 rating

Confidence interval: 1,411.57 – 1,423.98

11003 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
Claude Opus 4.1 (Thinking 16K, 20250805)
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-11-09 · rating

Claude Opus 4.1 (Thinking 16K, 20250805)

1,435.34 rating

Confidence interval: 1,429.60 – 1,441.09

13146 votes

Category
instruction_following
Evaluated configuration
Claude Opus 4.1 (Thinking 16K, 20250805)
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-11-09 · rating

Claude Opus 4.1 (Thinking 16K, 20250805)

1,377.75 rating

Confidence interval: 1,355.32 – 1,400.19

674 votes

Category
japanese
Evaluated configuration
Claude Opus 4.1 (Thinking 16K, 20250805)
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-11-09 · rating

Claude Opus 4.1 (Thinking 16K, 20250805)

1,380.84 rating

Confidence interval: 1,362.21 – 1,399.47

1100 votes

Category
korean
Evaluated configuration
Claude Opus 4.1 (Thinking 16K, 20250805)
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-11-09 · rating

Claude Opus 4.1 (Thinking 16K, 20250805)

1,454.75 rating

Confidence interval: 1,448.69 – 1,460.81

11435 votes

Category
longer_query
Evaluated configuration
Claude Opus 4.1 (Thinking 16K, 20250805)
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-11-09 · rating

Claude Opus 4.1 (Thinking 16K, 20250805)

1,431.04 rating

Confidence interval: 1,420.52 – 1,441.57

3038 votes

Category
math
Evaluated configuration
Claude Opus 4.1 (Thinking 16K, 20250805)
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-11-09 · rating

Claude Opus 4.1 (Thinking 16K, 20250805)

1,443.84 rating

Confidence interval: 1,436.99 – 1,450.68

8442 votes

Category
multi_turn
Evaluated configuration
Claude Opus 4.1 (Thinking 16K, 20250805)
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-11-09 · rating

Claude Opus 4.1 (Thinking 16K, 20250805)

1,403.72 rating

Confidence interval: 1,399.41 – 1,408.03

28500 votes

Category
non_english
Evaluated configuration
Claude Opus 4.1 (Thinking 16K, 20250805)
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-11-09 · rating

Claude Opus 4.1 (Thinking 16K, 20250805)

1,419.26 rating

Confidence interval: 1,415.80 – 1,422.72

49374 votes

Category
overall
Evaluated configuration
Claude Opus 4.1 (Thinking 16K, 20250805)
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-11-09 · rating

Claude Opus 4.1 (Thinking 16K, 20250805)

1,408.22 rating

Confidence interval: 1,395.72 – 1,420.72

2404 votes

Category
polish
Evaluated configuration
Claude Opus 4.1 (Thinking 16K, 20250805)
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-11-09 · rating

Claude Opus 4.1 (Thinking 16K, 20250805)

1,417.16 rating

Confidence interval: 1,408.16 – 1,426.16

4198 votes

Category
russian
Evaluated configuration
Claude Opus 4.1 (Thinking 16K, 20250805)
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-11-09 · rating

Claude Opus 4.1 (Thinking 16K, 20250805)

1,445.82 rating

Confidence interval: 1,428.48 – 1,463.16

1290 votes

Category
spanish
Evaluated configuration
Claude Opus 4.1 (Thinking 16K, 20250805)
Evaluation type
human preference

Run it locally

Inference · memory estimate

Claude Opus 4.1 (Thinking 16K, 20250805)

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license
Proprietary