GeekRadar / The comparison desk

COMPARE.

AI models

anthropic

Claude Opus 4.5 (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 (20251101) 1450.9 Claude Opus 4.5 (20251101) · 95% interval 1447.8–1454.0 · 72,825 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

Claude Opus 4.5 (20251101)

1,469.88 rating

Confidence interval: 1,461.40 – 1,478.37

5395 votes

Oct 28, 2026

Category: chinese
Evaluated configuration: Claude Opus 4.5 (20251101)
Evaluation type: human preference

Arena text preference / codinghuman preference · 2026-10-28 · rating

Claude Opus 4.5 (20251101)

1,498.24 rating

Confidence interval: 1,492.96 – 1,503.52

17954 votes

Oct 28, 2026

Category: coding
Evaluated configuration: Claude Opus 4.5 (20251101)
Evaluation type: human preference

Arena text preference / creative_writinghuman preference · 2026-10-28 · rating

Claude Opus 4.5 (20251101)

1,442.70 rating

Confidence interval: 1,436.37 – 1,449.03

11394 votes

Oct 28, 2026

Category: creative_writing
Evaluated configuration: Claude Opus 4.5 (20251101)
Evaluation type: human preference

Arena text preference / englishhuman preference · 2026-10-28 · rating

Claude Opus 4.5 (20251101)

1,460.56 rating

Confidence interval: 1,456.22 – 1,464.90

31197 votes

Oct 28, 2026

Category: english
Evaluated configuration: Claude Opus 4.5 (20251101)
Evaluation type: human preference

Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating

Claude Opus 4.5 (20251101)

1,449.31 rating

Confidence interval: 1,445.16 – 1,453.47

54030 votes

Oct 28, 2026

Category: exclude_ties
Evaluated configuration: Claude Opus 4.5 (20251101)
Evaluation type: human preference

Arena text preference / experthuman preference · 2026-10-28 · rating

Claude Opus 4.5 (20251101)

1,487.13 rating

Confidence interval: 1,478.89 – 1,495.37

5683 votes

Oct 28, 2026

Category: expert
Evaluated configuration: Claude Opus 4.5 (20251101)
Evaluation type: human preference

Arena text preference / frenchhuman preference · 2026-10-28 · rating

Claude Opus 4.5 (20251101)

1,471.58 rating

Confidence interval: 1,457.08 – 1,486.08

2021 votes

Oct 28, 2026

Category: french
Evaluated configuration: Claude Opus 4.5 (20251101)
Evaluation type: human preference

Arena text preference / germanhuman preference · 2026-10-28 · rating

Claude Opus 4.5 (20251101)

1,449.49 rating

Confidence interval: 1,431.38 – 1,467.60

1134 votes

Oct 28, 2026

Category: german
Evaluated configuration: Claude Opus 4.5 (20251101)
Evaluation type: human preference

Arena text preference / hard_promptshuman preference · 2026-10-28 · rating

Claude Opus 4.5 (20251101)

1,475.98 rating

Confidence interval: 1,472.05 – 1,479.91

43203 votes

Oct 28, 2026

Category: hard_prompts
Evaluated configuration: Claude Opus 4.5 (20251101)
Evaluation type: human preference

Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating

Claude Opus 4.5 (20251101)

1,481.59 rating

Confidence interval: 1,476.37 – 1,486.82

18751 votes

Oct 28, 2026

Category: hard_prompts_english
Evaluated configuration: Claude Opus 4.5 (20251101)
Evaluation type: human preference

Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating

Claude Opus 4.5 (20251101)

1,448.09 rating

Confidence interval: 1,442.37 – 1,453.81

14091 votes

Oct 28, 2026

Category: industry_business_and_management_and_financial_operations
Evaluated configuration: Claude Opus 4.5 (20251101)
Evaluation type: human preference

Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating

Claude Opus 4.5 (20251101)

1,433.88 rating

Confidence interval: 1,428.09 – 1,439.67

14064 votes

Oct 28, 2026

Category: industry_entertainment_and_sports_and_media
Evaluated configuration: Claude Opus 4.5 (20251101)
Evaluation type: human preference

Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating

Claude Opus 4.5 (20251101)

1,459.17 rating

Confidence interval: 1,450.72 – 1,467.62

5428 votes

Oct 28, 2026

Category: industry_legal_and_government
Evaluated configuration: Claude Opus 4.5 (20251101)
Evaluation type: human preference

Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating

Claude Opus 4.5 (20251101)

1,453.64 rating

Confidence interval: 1,447.53 – 1,459.76

11575 votes

Oct 28, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: Claude Opus 4.5 (20251101)
Evaluation type: human preference

Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating

Claude Opus 4.5 (20251101)

1,468.46 rating

Confidence interval: 1,458.53 – 1,478.39

3777 votes

Oct 28, 2026

Category: industry_mathematical
Evaluated configuration: Claude Opus 4.5 (20251101)
Evaluation type: human preference

Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating

Claude Opus 4.5 (20251101)

1,443.26 rating

Confidence interval: 1,434.39 – 1,452.13

4912 votes

Oct 28, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: Claude Opus 4.5 (20251101)
Evaluation type: human preference

Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating

Claude Opus 4.5 (20251101)

1,482.85 rating

Confidence interval: 1,478.28 – 1,487.41

26861 votes

Oct 28, 2026

Category: industry_software_and_it_services
Evaluated configuration: Claude Opus 4.5 (20251101)
Evaluation type: human preference

Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating

Claude Opus 4.5 (20251101)

1,451.26 rating

Confidence interval: 1,445.83 – 1,456.68

16893 votes

Oct 28, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: Claude Opus 4.5 (20251101)
Evaluation type: human preference

Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating

Claude Opus 4.5 (20251101)

1,472.37 rating

Confidence interval: 1,467.42 – 1,477.32

21809 votes

Oct 28, 2026

Category: instruction_following
Evaluated configuration: Claude Opus 4.5 (20251101)
Evaluation type: human preference

Arena text preference / japanesehuman preference · 2026-10-28 · rating

Claude Opus 4.5 (20251101)

1,411.38 rating

Confidence interval: 1,387.01 – 1,435.75

639 votes

Oct 28, 2026

Category: japanese
Evaluated configuration: Claude Opus 4.5 (20251101)
Evaluation type: human preference

Arena text preference / koreanhuman preference · 2026-10-28 · rating

Claude Opus 4.5 (20251101)

1,424.25 rating

Confidence interval: 1,406.11 – 1,442.39

1170 votes

Oct 28, 2026

Category: korean
Evaluated configuration: Claude Opus 4.5 (20251101)
Evaluation type: human preference

Arena text preference / longer_queryhuman preference · 2026-10-28 · rating

Claude Opus 4.5 (20251101)

1,478.87 rating

Confidence interval: 1,473.97 – 1,483.77

24213 votes

Oct 28, 2026

Category: longer_query
Evaluated configuration: Claude Opus 4.5 (20251101)
Evaluation type: human preference

Arena text preference / mathhuman preference · 2026-10-28 · rating

Claude Opus 4.5 (20251101)

1,458.08 rating

Confidence interval: 1,449.12 – 1,467.03

4547 votes

Oct 28, 2026

Category: math
Evaluated configuration: Claude Opus 4.5 (20251101)
Evaluation type: human preference

Arena text preference / multi_turnhuman preference · 2026-10-28 · rating

Claude Opus 4.5 (20251101)

1,466.09 rating

Confidence interval: 1,460.11 – 1,472.08

12956 votes

Oct 28, 2026

Category: multi_turn
Evaluated configuration: Claude Opus 4.5 (20251101)
Evaluation type: human preference

Arena text preference / non_englishhuman preference · 2026-10-28 · rating

Claude Opus 4.5 (20251101)

1,437.52 rating

Confidence interval: 1,433.64 – 1,441.40

41624 votes

Oct 28, 2026

Category: non_english
Evaluated configuration: Claude Opus 4.5 (20251101)
Evaluation type: human preference

Arena text preference / overallhuman preference · 2026-10-28 · rating

Claude Opus 4.5 (20251101)

1,450.90 rating

Confidence interval: 1,447.79 – 1,454.00

72825 votes

Oct 28, 2026

Category: overall
Evaluated configuration: Claude Opus 4.5 (20251101)
Evaluation type: human preference

Arena text preference / polishhuman preference · 2026-10-28 · rating

Claude Opus 4.5 (20251101)

1,438.71 rating

Confidence interval: 1,425.15 – 1,452.27

1891 votes

Oct 28, 2026

Category: polish
Evaluated configuration: Claude Opus 4.5 (20251101)
Evaluation type: human preference

Arena text preference / russianhuman preference · 2026-10-28 · rating

Claude Opus 4.5 (20251101)

1,447.02 rating

Confidence interval: 1,440.30 – 1,453.74

9041 votes

Oct 28, 2026

Category: russian
Evaluated configuration: Claude Opus 4.5 (20251101)
Evaluation type: human preference

Arena text preference / spanishhuman preference · 2026-10-28 · rating

Claude Opus 4.5 (20251101)

1,452.36 rating

Confidence interval: 1,438.88 – 1,465.84

2165 votes

Oct 28, 2026

Category: spanish
Evaluated configuration: Claude Opus 4.5 (20251101)
Evaluation type: human preference

Run it locally

Inference · memory estimate

Claude Opus 4.5 (20251101)

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license: Proprietary