GeekRadar / The comparison desk

COMPARE.

AI models

anthropic

Claude Opus 4 (Thinking 16K, 20250514)

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 (Thinking 16K, 20250514) 1377.1 Claude Opus 4 (Thinking 16K, 20250514) · 95% interval 1372.7–1381.6 · 35,852 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 (Thinking 16K, 20250514)

1,386.38 rating

Confidence interval: 1,374.04 – 1,398.73

2437 votes

Nov 9, 2026

Category: chinese
Evaluated configuration: Claude Opus 4 (Thinking 16K, 20250514)
Evaluation type: human preference

Arena text preference / codinghuman preference · 2026-11-09 · rating

Claude Opus 4 (Thinking 16K, 20250514)

1,442.19 rating

Confidence interval: 1,434.33 – 1,450.05

6583 votes

Nov 9, 2026

Category: coding
Evaluated configuration: Claude Opus 4 (Thinking 16K, 20250514)
Evaluation type: human preference

Arena text preference / creative_writinghuman preference · 2026-11-09 · rating

Claude Opus 4 (Thinking 16K, 20250514)

1,386.64 rating

Confidence interval: 1,377.35 – 1,395.92

4453 votes

Nov 9, 2026

Category: creative_writing
Evaluated configuration: Claude Opus 4 (Thinking 16K, 20250514)
Evaluation type: human preference

Arena text preference / englishhuman preference · 2026-11-09 · rating

Claude Opus 4 (Thinking 16K, 20250514)

1,385.93 rating

Confidence interval: 1,380.18 – 1,391.69

15470 votes

Nov 9, 2026

Category: english
Evaluated configuration: Claude Opus 4 (Thinking 16K, 20250514)
Evaluation type: human preference

Arena text preference / exclude_tieshuman preference · 2026-11-09 · rating

Claude Opus 4 (Thinking 16K, 20250514)

1,346.77 rating

Confidence interval: 1,340.96 – 1,352.58

26219 votes

Nov 9, 2026

Category: exclude_ties
Evaluated configuration: Claude Opus 4 (Thinking 16K, 20250514)
Evaluation type: human preference

Arena text preference / experthuman preference · 2026-11-09 · rating

Claude Opus 4 (Thinking 16K, 20250514)

1,385.21 rating

Confidence interval: 1,370.92 – 1,399.49

1765 votes

Nov 9, 2026

Category: expert
Evaluated configuration: Claude Opus 4 (Thinking 16K, 20250514)
Evaluation type: human preference

Arena text preference / frenchhuman preference · 2026-11-09 · rating

Claude Opus 4 (Thinking 16K, 20250514)

1,371.93 rating

Confidence interval: 1,345.20 – 1,398.66

523 votes

Nov 9, 2026

Category: french
Evaluated configuration: Claude Opus 4 (Thinking 16K, 20250514)
Evaluation type: human preference

Arena text preference / germanhuman preference · 2026-11-09 · rating

Claude Opus 4 (Thinking 16K, 20250514)

1,390.48 rating

Confidence interval: 1,370.71 – 1,410.25

956 votes

Nov 9, 2026

Category: german
Evaluated configuration: Claude Opus 4 (Thinking 16K, 20250514)
Evaluation type: human preference

Arena text preference / hard_promptshuman preference · 2026-11-09 · rating

Claude Opus 4 (Thinking 16K, 20250514)

1,399.52 rating

Confidence interval: 1,393.85 – 1,405.18

16167 votes

Nov 9, 2026

Category: hard_prompts
Evaluated configuration: Claude Opus 4 (Thinking 16K, 20250514)
Evaluation type: human preference

Arena text preference / hard_prompts_englishhuman preference · 2026-11-09 · rating

Claude Opus 4 (Thinking 16K, 20250514)

1,403.53 rating

Confidence interval: 1,396.01 – 1,411.05

7184 votes

Nov 9, 2026

Category: hard_prompts_english
Evaluated configuration: Claude Opus 4 (Thinking 16K, 20250514)
Evaluation type: human preference

Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-11-09 · rating

Claude Opus 4 (Thinking 16K, 20250514)

1,344.05 rating

Confidence interval: 1,335.89 – 1,352.22

5998 votes

Nov 9, 2026

Category: industry_business_and_management_and_financial_operations
Evaluated configuration: Claude Opus 4 (Thinking 16K, 20250514)
Evaluation type: human preference

Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-11-09 · rating

Claude Opus 4 (Thinking 16K, 20250514)

1,368.77 rating

Confidence interval: 1,360.82 – 1,376.72

6285 votes

Nov 9, 2026

Category: industry_entertainment_and_sports_and_media
Evaluated configuration: Claude Opus 4 (Thinking 16K, 20250514)
Evaluation type: human preference

Arena text preference / industry_legal_and_governmenthuman preference · 2026-11-09 · rating

Claude Opus 4 (Thinking 16K, 20250514)

1,366.52 rating

Confidence interval: 1,354.08 – 1,378.96

2422 votes

Nov 9, 2026

Category: industry_legal_and_government
Evaluated configuration: Claude Opus 4 (Thinking 16K, 20250514)
Evaluation type: human preference

Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-11-09 · rating

Claude Opus 4 (Thinking 16K, 20250514)

1,367.15 rating

Confidence interval: 1,358.89 – 1,375.41

5915 votes

Nov 9, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: Claude Opus 4 (Thinking 16K, 20250514)
Evaluation type: human preference

Arena text preference / industry_mathematicalhuman preference · 2026-11-09 · rating

Claude Opus 4 (Thinking 16K, 20250514)

1,392.00 rating

Confidence interval: 1,379.14 – 1,404.86

2044 votes

Nov 9, 2026

Category: industry_mathematical
Evaluated configuration: Claude Opus 4 (Thinking 16K, 20250514)
Evaluation type: human preference

Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-11-09 · rating

Claude Opus 4 (Thinking 16K, 20250514)

1,355.45 rating

Confidence interval: 1,342.38 – 1,368.53

2218 votes

Nov 9, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: Claude Opus 4 (Thinking 16K, 20250514)
Evaluation type: human preference

Arena text preference / industry_software_and_it_serviceshuman preference · 2026-11-09 · rating

Claude Opus 4 (Thinking 16K, 20250514)

1,408.81 rating

Confidence interval: 1,402.47 – 1,415.14

11704 votes

Nov 9, 2026

Category: industry_software_and_it_services
Evaluated configuration: Claude Opus 4 (Thinking 16K, 20250514)
Evaluation type: human preference

Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-11-09 · rating

Claude Opus 4 (Thinking 16K, 20250514)

1,392.10 rating

Confidence interval: 1,384.79 – 1,399.40

7809 votes

Nov 9, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: Claude Opus 4 (Thinking 16K, 20250514)
Evaluation type: human preference

Arena text preference / instruction_followinghuman preference · 2026-11-09 · rating

Claude Opus 4 (Thinking 16K, 20250514)

1,406.29 rating

Confidence interval: 1,399.40 – 1,413.17

9135 votes

Nov 9, 2026

Category: instruction_following
Evaluated configuration: Claude Opus 4 (Thinking 16K, 20250514)
Evaluation type: human preference

Arena text preference / japanesehuman preference · 2026-11-09 · rating

Claude Opus 4 (Thinking 16K, 20250514)

1,331.72 rating

Confidence interval: 1,309.85 – 1,353.58

830 votes

Nov 9, 2026

Category: japanese
Evaluated configuration: Claude Opus 4 (Thinking 16K, 20250514)
Evaluation type: human preference

Arena text preference / koreanhuman preference · 2026-11-09 · rating

Claude Opus 4 (Thinking 16K, 20250514)

1,319.88 rating

Confidence interval: 1,297.78 – 1,341.98

790 votes

Nov 9, 2026

Category: korean
Evaluated configuration: Claude Opus 4 (Thinking 16K, 20250514)
Evaluation type: human preference

Arena text preference / longer_queryhuman preference · 2026-11-09 · rating

Claude Opus 4 (Thinking 16K, 20250514)

1,422.16 rating

Confidence interval: 1,414.50 – 1,429.81

6961 votes

Nov 9, 2026

Category: longer_query
Evaluated configuration: Claude Opus 4 (Thinking 16K, 20250514)
Evaluation type: human preference

Arena text preference / mathhuman preference · 2026-11-09 · rating

Claude Opus 4 (Thinking 16K, 20250514)

1,390.47 rating

Confidence interval: 1,378.21 – 1,402.73

2226 votes

Nov 9, 2026

Category: math
Evaluated configuration: Claude Opus 4 (Thinking 16K, 20250514)
Evaluation type: human preference

Arena text preference / multi_turnhuman preference · 2026-11-09 · rating

Claude Opus 4 (Thinking 16K, 20250514)

1,395.66 rating

Confidence interval: 1,387.44 – 1,403.88

6039 votes

Nov 9, 2026

Category: multi_turn
Evaluated configuration: Claude Opus 4 (Thinking 16K, 20250514)
Evaluation type: human preference

Arena text preference / non_englishhuman preference · 2026-11-09 · rating

Claude Opus 4 (Thinking 16K, 20250514)

1,361.64 rating

Confidence interval: 1,356.32 – 1,366.96

20370 votes

Nov 9, 2026

Category: non_english
Evaluated configuration: Claude Opus 4 (Thinking 16K, 20250514)
Evaluation type: human preference

Arena text preference / overallhuman preference · 2026-11-09 · rating

Claude Opus 4 (Thinking 16K, 20250514)

1,377.15 rating

Confidence interval: 1,372.71 – 1,381.59

35852 votes

Nov 9, 2026

Category: overall
Evaluated configuration: Claude Opus 4 (Thinking 16K, 20250514)
Evaluation type: human preference

Arena text preference / polishhuman preference · 2026-11-09 · rating

Claude Opus 4 (Thinking 16K, 20250514)

1,355.56 rating

Confidence interval: 1,344.60 – 1,366.52

3569 votes

Nov 9, 2026

Category: polish
Evaluated configuration: Claude Opus 4 (Thinking 16K, 20250514)
Evaluation type: human preference

Arena text preference / russianhuman preference · 2026-11-09 · rating

Claude Opus 4 (Thinking 16K, 20250514)

1,391.74 rating

Confidence interval: 1,380.26 – 1,403.23

2550 votes

Nov 9, 2026

Category: russian
Evaluated configuration: Claude Opus 4 (Thinking 16K, 20250514)
Evaluation type: human preference

Arena text preference / spanishhuman preference · 2026-11-09 · rating

Claude Opus 4 (Thinking 16K, 20250514)

1,388.93 rating

Confidence interval: 1,368.41 – 1,409.44

857 votes

Nov 9, 2026

Category: spanish
Evaluated configuration: Claude Opus 4 (Thinking 16K, 20250514)
Evaluation type: human preference

Run it locally

Inference · memory estimate

Claude Opus 4 (Thinking 16K, 20250514)

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license: Proprietary