GeekRadar / The comparison desk

COMPARE.

AI models

anthropic

Claude Opus 4.5 (High, 32K, 20251101)

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 4.5 (High, 32K, 20251101) 1448.3 Claude Opus 4.5 (High, 32K, 20251101) · 95% interval 1444.5–1452.1 · 37,460 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 4.5 (High, 32K, 20251101)

1,467.20 rating

Confidence interval: 1,456.32 – 1,478.08

3040 votes

Nov 6, 2026

Category: chinese
Evaluated configuration: Claude Opus 4.5 (High, 32K, 20251101)
Evaluation type: human preference

Arena text preference / codinghuman preference · 2026-11-06 · rating

Claude Opus 4.5 (High, 32K, 20251101)

1,503.39 rating

Confidence interval: 1,496.23 – 1,510.55

7778 votes

Nov 6, 2026

Category: coding
Evaluated configuration: Claude Opus 4.5 (High, 32K, 20251101)
Evaluation type: human preference

Arena text preference / creative_writinghuman preference · 2026-11-06 · rating

Claude Opus 4.5 (High, 32K, 20251101)

1,445.06 rating

Confidence interval: 1,436.82 – 1,453.30

5686 votes

Nov 6, 2026

Category: creative_writing
Evaluated configuration: Claude Opus 4.5 (High, 32K, 20251101)
Evaluation type: human preference

Arena text preference / englishhuman preference · 2026-11-06 · rating

Claude Opus 4.5 (High, 32K, 20251101)

1,456.04 rating

Confidence interval: 1,450.44 – 1,461.64

14849 votes

Nov 6, 2026

Category: english
Evaluated configuration: Claude Opus 4.5 (High, 32K, 20251101)
Evaluation type: human preference

Arena text preference / exclude_tieshuman preference · 2026-11-06 · rating

Claude Opus 4.5 (High, 32K, 20251101)

1,446.58 rating

Confidence interval: 1,441.32 – 1,451.85

27067 votes

Nov 6, 2026

Category: exclude_ties
Evaluated configuration: Claude Opus 4.5 (High, 32K, 20251101)
Evaluation type: human preference

Arena text preference / experthuman preference · 2026-11-06 · rating

Claude Opus 4.5 (High, 32K, 20251101)

1,481.20 rating

Confidence interval: 1,469.19 – 1,493.22

2424 votes

Nov 6, 2026

Category: expert
Evaluated configuration: Claude Opus 4.5 (High, 32K, 20251101)
Evaluation type: human preference

Arena text preference / frenchhuman preference · 2026-11-06 · rating

Claude Opus 4.5 (High, 32K, 20251101)

1,457.69 rating

Confidence interval: 1,436.66 – 1,478.72

849 votes

Nov 6, 2026

Category: french
Evaluated configuration: Claude Opus 4.5 (High, 32K, 20251101)
Evaluation type: human preference

Arena text preference / germanhuman preference · 2026-11-06 · rating

Claude Opus 4.5 (High, 32K, 20251101)

1,440.40 rating

Confidence interval: 1,417.35 – 1,463.44

666 votes

Nov 6, 2026

Category: german
Evaluated configuration: Claude Opus 4.5 (High, 32K, 20251101)
Evaluation type: human preference

Arena text preference / hard_promptshuman preference · 2026-11-06 · rating

Claude Opus 4.5 (High, 32K, 20251101)

1,473.47 rating

Confidence interval: 1,468.45 – 1,478.48

20284 votes

Nov 6, 2026

Category: hard_prompts
Evaluated configuration: Claude Opus 4.5 (High, 32K, 20251101)
Evaluation type: human preference

Arena text preference / hard_prompts_englishhuman preference · 2026-11-06 · rating

Claude Opus 4.5 (High, 32K, 20251101)

1,477.18 rating

Confidence interval: 1,470.03 – 1,484.33

7831 votes

Nov 6, 2026

Category: hard_prompts_english
Evaluated configuration: Claude Opus 4.5 (High, 32K, 20251101)
Evaluation type: human preference

Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-11-06 · rating

Claude Opus 4.5 (High, 32K, 20251101)

1,433.64 rating

Confidence interval: 1,426.16 – 1,441.11

7032 votes

Nov 6, 2026

Category: industry_business_and_management_and_financial_operations
Evaluated configuration: Claude Opus 4.5 (High, 32K, 20251101)
Evaluation type: human preference

Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-11-06 · rating

Claude Opus 4.5 (High, 32K, 20251101)

1,425.81 rating

Confidence interval: 1,418.32 – 1,433.29

6920 votes

Nov 6, 2026

Category: industry_entertainment_and_sports_and_media
Evaluated configuration: Claude Opus 4.5 (High, 32K, 20251101)
Evaluation type: human preference

Arena text preference / industry_legal_and_governmenthuman preference · 2026-11-06 · rating

Claude Opus 4.5 (High, 32K, 20251101)

1,454.41 rating

Confidence interval: 1,443.16 – 1,465.67

2777 votes

Nov 6, 2026

Category: industry_legal_and_government
Evaluated configuration: Claude Opus 4.5 (High, 32K, 20251101)
Evaluation type: human preference

Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-11-06 · rating

Claude Opus 4.5 (High, 32K, 20251101)

1,447.88 rating

Confidence interval: 1,439.88 – 1,455.88

6044 votes

Nov 6, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: Claude Opus 4.5 (High, 32K, 20251101)
Evaluation type: human preference

Arena text preference / industry_mathematicalhuman preference · 2026-11-06 · rating

Claude Opus 4.5 (High, 32K, 20251101)

1,459.04 rating

Confidence interval: 1,444.75 – 1,473.33

1665 votes

Nov 6, 2026

Category: industry_mathematical
Evaluated configuration: Claude Opus 4.5 (High, 32K, 20251101)
Evaluation type: human preference

Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-11-06 · rating

Claude Opus 4.5 (High, 32K, 20251101)

1,431.48 rating

Confidence interval: 1,419.20 – 1,443.76

2423 votes

Nov 6, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: Claude Opus 4.5 (High, 32K, 20251101)
Evaluation type: human preference

Arena text preference / industry_software_and_it_serviceshuman preference · 2026-11-06 · rating

Claude Opus 4.5 (High, 32K, 20251101)

1,482.31 rating

Confidence interval: 1,476.38 – 1,488.23

12632 votes

Nov 6, 2026

Category: industry_software_and_it_services
Evaluated configuration: Claude Opus 4.5 (High, 32K, 20251101)
Evaluation type: human preference

Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-11-06 · rating

Claude Opus 4.5 (High, 32K, 20251101)

1,444.97 rating

Confidence interval: 1,438.01 – 1,451.93

8582 votes

Nov 6, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: Claude Opus 4.5 (High, 32K, 20251101)
Evaluation type: human preference

Arena text preference / instruction_followinghuman preference · 2026-11-06 · rating

Claude Opus 4.5 (High, 32K, 20251101)

1,478.17 rating

Confidence interval: 1,471.55 – 1,484.79

9872 votes

Nov 6, 2026

Category: instruction_following
Evaluated configuration: Claude Opus 4.5 (High, 32K, 20251101)
Evaluation type: human preference

Arena text preference / japanesehuman preference · 2026-11-06 · rating

Claude Opus 4.5 (High, 32K, 20251101)

1,417.20 rating

Confidence interval: 1,385.61 – 1,448.79

378 votes

Nov 6, 2026

Category: japanese
Evaluated configuration: Claude Opus 4.5 (High, 32K, 20251101)
Evaluation type: human preference

Arena text preference / koreanhuman preference · 2026-11-06 · rating

Claude Opus 4.5 (High, 32K, 20251101)

1,377.45 rating

Confidence interval: 1,352.41 – 1,402.49

580 votes

Nov 6, 2026

Category: korean
Evaluated configuration: Claude Opus 4.5 (High, 32K, 20251101)
Evaluation type: human preference

Arena text preference / longer_queryhuman preference · 2026-11-06 · rating

Claude Opus 4.5 (High, 32K, 20251101)

1,478.60 rating

Confidence interval: 1,472.01 – 1,485.18

9822 votes

Nov 6, 2026

Category: longer_query
Evaluated configuration: Claude Opus 4.5 (High, 32K, 20251101)
Evaluation type: human preference

Arena text preference / mathhuman preference · 2026-11-06 · rating

Claude Opus 4.5 (High, 32K, 20251101)

1,462.64 rating

Confidence interval: 1,450.57 – 1,474.72

2344 votes

Nov 6, 2026

Category: math
Evaluated configuration: Claude Opus 4.5 (High, 32K, 20251101)
Evaluation type: human preference

Arena text preference / multi_turnhuman preference · 2026-11-06 · rating

Claude Opus 4.5 (High, 32K, 20251101)

1,460.17 rating

Confidence interval: 1,452.37 – 1,467.97

6504 votes

Nov 6, 2026

Category: multi_turn
Evaluated configuration: Claude Opus 4.5 (High, 32K, 20251101)
Evaluation type: human preference

Arena text preference / non_englishhuman preference · 2026-11-06 · rating

Claude Opus 4.5 (High, 32K, 20251101)

1,435.39 rating

Confidence interval: 1,430.61 – 1,440.17

22605 votes

Nov 6, 2026

Category: non_english
Evaluated configuration: Claude Opus 4.5 (High, 32K, 20251101)
Evaluation type: human preference

Arena text preference / overallhuman preference · 2026-11-06 · rating

Claude Opus 4.5 (High, 32K, 20251101)

1,448.31 rating

Confidence interval: 1,444.48 – 1,452.14

37460 votes

Nov 6, 2026

Category: overall
Evaluated configuration: Claude Opus 4.5 (High, 32K, 20251101)
Evaluation type: human preference

Arena text preference / polishhuman preference · 2026-11-06 · rating

Claude Opus 4.5 (High, 32K, 20251101)

1,438.23 rating

Confidence interval: 1,420.46 – 1,456.00

1097 votes

Nov 6, 2026

Category: polish
Evaluated configuration: Claude Opus 4.5 (High, 32K, 20251101)
Evaluation type: human preference

Arena text preference / russianhuman preference · 2026-11-06 · rating

Claude Opus 4.5 (High, 32K, 20251101)

1,436.94 rating

Confidence interval: 1,428.27 – 1,445.62

4820 votes

Nov 6, 2026

Category: russian
Evaluated configuration: Claude Opus 4.5 (High, 32K, 20251101)
Evaluation type: human preference

Arena text preference / spanishhuman preference · 2026-11-06 · rating

Claude Opus 4.5 (High, 32K, 20251101)

1,457.36 rating

Confidence interval: 1,439.71 – 1,475.01

1146 votes

Nov 6, 2026

Category: spanish
Evaluated configuration: Claude Opus 4.5 (High, 32K, 20251101)
Evaluation type: human preference

Run it locally

Inference · memory estimate

Claude Opus 4.5 (High, 32K, 20251101)

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license: Proprietary