GeekRadar / The comparison desk

Claude Opus 4 vs Claude Sonnet 4

Catalog Differences only

Capability & preference

General capability · ECI

A cross-benchmark capability estimate. Index points, not a percentage; intervals show uncertainty.

Claude Opus 4 142.4^* Claude Opus 4 · 95% interval 140.2–144.1

Claude Sonnet 4 141.6^* Claude Sonnet 4 · 95% interval 138.8–142.9

Human preference · Arena

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

Claude Opus 4 1365.9 claude-opus-4-20250514 · 95% interval 1361.6–1370.2 · 43,043 votes · 2026-10-15

Claude Sonnet 4 1339.2 claude-sonnet-4-20250514 · 95% interval 1334.8–1343.7 · 39,163 votes · 2026-10-15

Model performance

Radar task score: four tests, equal weight. An experimental summary of these tasks, not a universal intelligence rating.

Claude Opus 4

Tested configuration Radar task score

Unrated

1/4 core tests · not enough evidence

1 benchmark results for this configuration

Claude Sonnet 4

Tested configuration Radar task score

Unrated

1/4 core tests · not enough evidence

1 benchmark results for this configuration

Scientific reasoning

GPQA Diamond · 25%

Expert-written science questions; strict multiple-choice scoring. Chance accuracy is 25%.

Claude Opus 4 76.3^*% Approx. 95% interval: 70.3–82.2% · 2025-05-22 · Older result

Claude Sonnet 4 77.8^*% Approx. 95% interval: 72.6–83.1% · 2025-05-26 · Older result

Novel problem solving

Mystery Game Puzzles · 25%

Best-next-move puzzles in an undisclosed game variant. A narrow reasoning test, not general intelligence.

Claude Opus 4 Not available

Claude Sonnet 4 Not available

Advanced mathematics

FrontierMath Tiers 1-3 · 25%

Private v2 mathematics problems with Python tools. Earlier versions and Tier 4 are excluded.

Claude Opus 4 Not available

Claude Sonnet 4 Not available

Factual answers

SimpleQA Verified · 25%

Correct factual answers under a guessing prompt, graded by a model. Not a hallucination or abstention score.

Claude Opus 4 Not available

Claude Sonnet 4 Not available

Bars show reported task scores. Whiskers are approximate 95% intervals where standard errors are available. Different reasoning budgets are not equal-cost tests. Missing results are never zero.

Run it locally

Inference · memory estimate

Claude Opus 4

Closed weights. No supported local deployment or GPU requirement is published.

Claude Sonnet 4

Closed weights. No supported local deployment or GPU requirement is published.

Claude Opus 4 vs Claude Sonnet 4
At a glance	Models Claude Opus 4 anthropic	Models Claude Sonnet 4 anthropic
Release date	2025-05-22	2025-05-22
Capabilities
Context window	200,000 tokens	200,000 tokens
Maximum output	32,000 tokens	64,000 tokens
Reasoning	Yes	Yes
Tool calling	Yes	Yes
Open weights	No	No
Knowledge cutoff	2025-03-31	2025-03-31
Model license	Proprietary	Proprietary
Input modalities	text image pdf	text image pdf
Output modalities	text	text

API cost

USD / month

Input tokens / monthOutput tokens / month

Standard text-token estimate. Excludes taxes, caching, batch discounts, reasoning and multimodal surcharges. Provider limits and regional availability may differ.

Claude Opus 4

Provider offer

Claude Sonnet 4

Provider offer

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 · 2026-10-15 · rating

Claude Opus 4

1,386.55 rating

Confidence interval: 1,374.21 – 1,398.89

2438 votes

Oct 15, 2026

Category: chinese
Evaluated configuration: claude-opus-4-20250514-thinking-16k
Evaluation type: human preference

1,382.00 rating

Confidence interval: 1,370.96 – 1,393.04

3098 votes

Oct 15, 2026

Category: chinese
Evaluated configuration: claude-opus-4-20250514
Evaluation type: human preference

Claude Sonnet 4

1,350.03 rating

Confidence interval: 1,337.68 – 1,362.38

2376 votes

Oct 15, 2026

Category: chinese
Evaluated configuration: claude-sonnet-4-20250514-thinking-32k
Evaluation type: human preference

1,340.69 rating

Confidence interval: 1,329.06 – 1,352.32

2842 votes

Oct 15, 2026

Category: chinese
Evaluated configuration: claude-sonnet-4-20250514
Evaluation type: human preference

Arena text preference / codinghuman preference · 2026-10-15 · rating

Claude Opus 4

1,442.13 rating

Confidence interval: 1,434.28 – 1,449.98

6596 votes

Oct 15, 2026

Category: coding
Evaluated configuration: claude-opus-4-20250514-thinking-16k
Evaluation type: human preference

1,401.46 rating

Confidence interval: 1,394.23 – 1,408.70

7833 votes

Oct 15, 2026

Category: coding
Evaluated configuration: claude-opus-4-20250514
Evaluation type: human preference

Claude Sonnet 4

1,414.15 rating

Confidence interval: 1,406.26 – 1,422.04

6348 votes

Oct 15, 2026

Category: coding
Evaluated configuration: claude-sonnet-4-20250514-thinking-32k
Evaluation type: human preference

1,379.18 rating

Confidence interval: 1,371.79 – 1,386.58

7307 votes

Oct 15, 2026

Category: coding
Evaluated configuration: claude-sonnet-4-20250514
Evaluation type: human preference

Arena text preference / creative_writinghuman preference · 2026-10-15 · rating

Claude Opus 4

1,386.15 rating

Confidence interval: 1,376.87 – 1,395.42

4461 votes

Oct 15, 2026

Category: creative_writing
Evaluated configuration: claude-opus-4-20250514-thinking-16k
Evaluation type: human preference

1,374.78 rating

Confidence interval: 1,366.21 – 1,383.35

5412 votes

Oct 15, 2026

Category: creative_writing
Evaluated configuration: claude-opus-4-20250514
Evaluation type: human preference

Claude Sonnet 4

1,344.99 rating

Confidence interval: 1,335.50 – 1,354.47

4248 votes

Oct 15, 2026

Category: creative_writing
Evaluated configuration: claude-sonnet-4-20250514-thinking-32k
Evaluation type: human preference

1,342.18 rating

Confidence interval: 1,333.28 – 1,351.09

4905 votes

Oct 15, 2026

Category: creative_writing
Evaluated configuration: claude-sonnet-4-20250514
Evaluation type: human preference

Arena text preference / englishhuman preference · 2026-10-15 · rating

Claude Opus 4

1,385.95 rating

Confidence interval: 1,380.20 – 1,391.69

15505 votes

Oct 15, 2026

Category: english
Evaluated configuration: claude-opus-4-20250514-thinking-16k
Evaluation type: human preference

1,375.61 rating

Confidence interval: 1,370.10 – 1,381.12

19052 votes

Oct 15, 2026

Category: english
Evaluated configuration: claude-opus-4-20250514
Evaluation type: human preference

Claude Sonnet 4

1,364.41 rating

Confidence interval: 1,358.61 – 1,370.22

14847 votes

Oct 15, 2026

Category: english
Evaluated configuration: claude-sonnet-4-20250514-thinking-32k
Evaluation type: human preference

1,343.93 rating

Confidence interval: 1,338.30 – 1,349.56

17205 votes

Oct 15, 2026

Category: english
Evaluated configuration: claude-sonnet-4-20250514
Evaluation type: human preference

Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating

Claude Opus 4

1,346.73 rating

Confidence interval: 1,340.93 – 1,352.53

26252 votes

Oct 15, 2026

Category: exclude_ties
Evaluated configuration: claude-opus-4-20250514-thinking-16k
Evaluation type: human preference

1,331.61 rating

Confidence interval: 1,325.92 – 1,337.30

31139 votes

Oct 15, 2026

Category: exclude_ties
Evaluated configuration: claude-opus-4-20250514
Evaluation type: human preference

Claude Sonnet 4

1,311.07 rating

Confidence interval: 1,305.19 – 1,316.95

25040 votes

Oct 15, 2026

Category: exclude_ties
Evaluated configuration: claude-sonnet-4-20250514-thinking-32k
Evaluation type: human preference

1,295.04 rating

Confidence interval: 1,289.24 – 1,300.83

28586 votes

Oct 15, 2026

Category: exclude_ties
Evaluated configuration: claude-sonnet-4-20250514
Evaluation type: human preference

Arena text preference / experthuman preference · 2026-10-15 · rating

Claude Opus 4

1,385.65 rating

Confidence interval: 1,371.38 – 1,399.92

1766 votes

Oct 15, 2026

Category: expert
Evaluated configuration: claude-opus-4-20250514-thinking-16k
Evaluation type: human preference

1,369.35 rating

Confidence interval: 1,356.92 – 1,381.78

2283 votes

Oct 15, 2026

Category: expert
Evaluated configuration: claude-opus-4-20250514
Evaluation type: human preference

Claude Sonnet 4

1,372.22 rating

Confidence interval: 1,357.75 – 1,386.69

1702 votes

Oct 15, 2026

Category: expert
Evaluated configuration: claude-sonnet-4-20250514-thinking-32k
Evaluation type: human preference

1,335.31 rating

Confidence interval: 1,322.10 – 1,348.52

2091 votes

Oct 15, 2026

Category: expert
Evaluated configuration: claude-sonnet-4-20250514
Evaluation type: human preference

Arena text preference / frenchhuman preference · 2026-10-15 · rating

Claude Opus 4

1,371.71 rating

Confidence interval: 1,344.95 – 1,398.47

521 votes

Oct 15, 2026

Category: french
Evaluated configuration: claude-opus-4-20250514-thinking-16k
Evaluation type: human preference

1,359.38 rating

Confidence interval: 1,334.96 – 1,383.81

630 votes

Oct 15, 2026

Category: french
Evaluated configuration: claude-opus-4-20250514
Evaluation type: human preference

Claude Sonnet 4

1,363.06 rating

Confidence interval: 1,337.82 – 1,388.30

570 votes

Oct 15, 2026

Category: french
Evaluated configuration: claude-sonnet-4-20250514
Evaluation type: human preference

1,355.67 rating

Confidence interval: 1,328.85 – 1,382.50

472 votes

Oct 15, 2026

Category: french
Evaluated configuration: claude-sonnet-4-20250514-thinking-32k
Evaluation type: human preference

Arena text preference / germanhuman preference · 2026-10-15 · rating

Claude Opus 4

1,390.82 rating

Confidence interval: 1,371.06 – 1,410.58

955 votes

Oct 15, 2026

Category: german
Evaluated configuration: claude-opus-4-20250514-thinking-16k
Evaluation type: human preference

1,372.01 rating

Confidence interval: 1,354.88 – 1,389.15

1273 votes

Oct 15, 2026

Category: german
Evaluated configuration: claude-opus-4-20250514
Evaluation type: human preference

Claude Sonnet 4

1,330.94 rating

Confidence interval: 1,312.20 – 1,349.68

1081 votes

Oct 15, 2026

Category: german
Evaluated configuration: claude-sonnet-4-20250514
Evaluation type: human preference

1,317.39 rating

Confidence interval: 1,296.51 – 1,338.27

860 votes

Oct 15, 2026

Category: german
Evaluated configuration: claude-sonnet-4-20250514-thinking-32k
Evaluation type: human preference

Arena text preference / hard_promptshuman preference · 2026-10-15 · rating

Claude Opus 4

1,399.25 rating

Confidence interval: 1,393.59 – 1,404.91

16192 votes

Oct 15, 2026

Category: hard_prompts
Evaluated configuration: claude-opus-4-20250514-thinking-16k
Evaluation type: human preference

1,376.43 rating

Confidence interval: 1,370.99 – 1,381.87

18934 votes

Oct 15, 2026

Category: hard_prompts
Evaluated configuration: claude-opus-4-20250514
Evaluation type: human preference

Claude Sonnet 4

1,372.43 rating

Confidence interval: 1,366.70 – 1,378.15

15413 votes

Oct 15, 2026

Category: hard_prompts
Evaluated configuration: claude-sonnet-4-20250514-thinking-32k
Evaluation type: human preference

1,354.86 rating

Confidence interval: 1,349.27 – 1,360.45

17418 votes

Oct 15, 2026

Category: hard_prompts
Evaluated configuration: claude-sonnet-4-20250514
Evaluation type: human preference

Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating

Claude Opus 4

1,403.50 rating

Confidence interval: 1,395.99 – 1,411.01

7201 votes

Oct 15, 2026

Category: hard_prompts_english
Evaluated configuration: claude-opus-4-20250514-thinking-16k
Evaluation type: human preference

1,381.82 rating

Confidence interval: 1,374.75 – 1,388.88

8515 votes

Oct 15, 2026

Category: hard_prompts_english
Evaluated configuration: claude-opus-4-20250514
Evaluation type: human preference

Claude Sonnet 4

1,384.99 rating

Confidence interval: 1,377.36 – 1,392.61

6982 votes

Oct 15, 2026

Category: hard_prompts_english
Evaluated configuration: claude-sonnet-4-20250514-thinking-32k
Evaluation type: human preference

1,358.55 rating

Confidence interval: 1,351.28 – 1,365.81

7899 votes

Oct 15, 2026

Category: hard_prompts_english
Evaluated configuration: claude-sonnet-4-20250514
Evaluation type: human preference

Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating

Claude Opus 4

1,344.31 rating

Confidence interval: 1,336.15 – 1,352.47

6001 votes

Oct 15, 2026

Category: industry_business_and_management_and_financial_operations
Evaluated configuration: claude-opus-4-20250514-thinking-16k
Evaluation type: human preference

1,337.37 rating

Confidence interval: 1,329.61 – 1,345.13

7045 votes

Oct 15, 2026

Category: industry_business_and_management_and_financial_operations
Evaluated configuration: claude-opus-4-20250514
Evaluation type: human preference

Claude Sonnet 4

1,318.44 rating

Confidence interval: 1,310.44 – 1,326.44

6541 votes

Oct 15, 2026

Category: industry_business_and_management_and_financial_operations
Evaluated configuration: claude-sonnet-4-20250514
Evaluation type: human preference

1,314.20 rating

Confidence interval: 1,305.82 – 1,322.58

5771 votes

Oct 15, 2026

Category: industry_business_and_management_and_financial_operations
Evaluated configuration: claude-sonnet-4-20250514-thinking-32k
Evaluation type: human preference

Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating

Claude Opus 4

1,368.70 rating

Confidence interval: 1,360.77 – 1,376.63

6300 votes

Oct 15, 2026

Category: industry_entertainment_and_sports_and_media
Evaluated configuration: claude-opus-4-20250514-thinking-16k
Evaluation type: human preference

1,350.11 rating

Confidence interval: 1,342.73 – 1,357.50

7526 votes

Oct 15, 2026

Category: industry_entertainment_and_sports_and_media
Evaluated configuration: claude-opus-4-20250514
Evaluation type: human preference

Claude Sonnet 4

1,331.88 rating

Confidence interval: 1,323.83 – 1,339.94

6040 votes

Oct 15, 2026

Category: industry_entertainment_and_sports_and_media
Evaluated configuration: claude-sonnet-4-20250514-thinking-32k
Evaluation type: human preference

1,320.30 rating

Confidence interval: 1,312.52 – 1,328.07

6850 votes

Oct 15, 2026

Category: industry_entertainment_and_sports_and_media
Evaluated configuration: claude-sonnet-4-20250514
Evaluation type: human preference

Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating

Claude Opus 4

1,372.79 rating

Confidence interval: 1,361.49 – 1,384.09

2851 votes

Oct 15, 2026

Category: industry_legal_and_government
Evaluated configuration: claude-opus-4-20250514
Evaluation type: human preference

1,366.22 rating

Confidence interval: 1,353.78 – 1,378.65

2422 votes

Oct 15, 2026

Category: industry_legal_and_government
Evaluated configuration: claude-opus-4-20250514-thinking-16k
Evaluation type: human preference

Claude Sonnet 4

1,341.45 rating

Confidence interval: 1,329.33 – 1,353.58

2622 votes

Oct 15, 2026

Category: industry_legal_and_government
Evaluated configuration: claude-sonnet-4-20250514
Evaluation type: human preference

1,336.60 rating

Confidence interval: 1,323.44 – 1,349.77

2207 votes

Oct 15, 2026

Category: industry_legal_and_government
Evaluated configuration: claude-sonnet-4-20250514-thinking-32k
Evaluation type: human preference

Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating

Claude Opus 4

1,367.23 rating

Confidence interval: 1,358.98 – 1,375.48

5921 votes

Oct 15, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: claude-opus-4-20250514-thinking-16k
Evaluation type: human preference

1,362.84 rating

Confidence interval: 1,355.05 – 1,370.64

6982 votes

Oct 15, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: claude-opus-4-20250514
Evaluation type: human preference

Claude Sonnet 4

1,345.69 rating

Confidence interval: 1,337.34 – 1,354.04

5611 votes

Oct 15, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: claude-sonnet-4-20250514-thinking-32k
Evaluation type: human preference

1,339.93 rating

Confidence interval: 1,331.85 – 1,348.01

6379 votes

Oct 15, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: claude-sonnet-4-20250514
Evaluation type: human preference

Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating

Claude Opus 4

1,391.39 rating

Confidence interval: 1,378.56 – 1,404.23

2051 votes

Oct 15, 2026

Category: industry_mathematical
Evaluated configuration: claude-opus-4-20250514-thinking-16k
Evaluation type: human preference

1,376.07 rating

Confidence interval: 1,364.59 – 1,387.55

2622 votes

Oct 15, 2026

Category: industry_mathematical
Evaluated configuration: claude-opus-4-20250514
Evaluation type: human preference

Claude Sonnet 4

1,379.22 rating

Confidence interval: 1,365.88 – 1,392.57

1915 votes

Oct 15, 2026

Category: industry_mathematical
Evaluated configuration: claude-sonnet-4-20250514-thinking-32k
Evaluation type: human preference

1,357.73 rating

Confidence interval: 1,345.40 – 1,370.06

2322 votes

Oct 15, 2026

Category: industry_mathematical
Evaluated configuration: claude-sonnet-4-20250514
Evaluation type: human preference

Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating

Claude Opus 4

1,365.30 rating

Confidence interval: 1,353.16 – 1,377.45

2609 votes

Oct 15, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: claude-opus-4-20250514
Evaluation type: human preference

1,356.24 rating

Confidence interval: 1,343.18 – 1,369.30

2221 votes

Oct 15, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: claude-opus-4-20250514-thinking-16k
Evaluation type: human preference

Claude Sonnet 4

1,330.51 rating

Confidence interval: 1,317.51 – 1,343.51

2364 votes

Oct 15, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: claude-sonnet-4-20250514
Evaluation type: human preference

1,326.35 rating

Confidence interval: 1,312.98 – 1,339.73

2123 votes

Oct 15, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: claude-sonnet-4-20250514-thinking-32k
Evaluation type: human preference

Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating

Claude Opus 4

1,408.74 rating

Confidence interval: 1,402.41 – 1,415.06

11721 votes

Oct 15, 2026

Category: industry_software_and_it_services
Evaluated configuration: claude-opus-4-20250514-thinking-16k
Evaluation type: human preference

1,381.30 rating

Confidence interval: 1,375.32 – 1,387.27

14221 votes

Oct 15, 2026

Category: industry_software_and_it_services
Evaluated configuration: claude-opus-4-20250514
Evaluation type: human preference

Claude Sonnet 4

1,383.69 rating

Confidence interval: 1,377.33 – 1,390.04

11254 votes

Oct 15, 2026

Category: industry_software_and_it_services
Evaluated configuration: claude-sonnet-4-20250514-thinking-32k
Evaluation type: human preference

1,360.64 rating

Confidence interval: 1,354.55 – 1,366.73

13140 votes

Oct 15, 2026

Category: industry_software_and_it_services
Evaluated configuration: claude-sonnet-4-20250514
Evaluation type: human preference

Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating

Claude Opus 4

1,391.67 rating

Confidence interval: 1,384.37 – 1,398.97

7825 votes

Oct 15, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: claude-opus-4-20250514-thinking-16k
Evaluation type: human preference

1,381.60 rating

Confidence interval: 1,374.67 – 1,388.53

9302 votes

Oct 15, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: claude-opus-4-20250514
Evaluation type: human preference

Claude Sonnet 4

1,356.91 rating

Confidence interval: 1,349.50 – 1,364.31

7373 votes

Oct 15, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: claude-sonnet-4-20250514-thinking-32k
Evaluation type: human preference

1,350.85 rating

Confidence interval: 1,343.76 – 1,357.93

8500 votes

Oct 15, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: claude-sonnet-4-20250514
Evaluation type: human preference

Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating

Claude Opus 4

1,406.21 rating

Confidence interval: 1,399.33 – 1,413.09

9149 votes

Oct 15, 2026

Category: instruction_following
Evaluated configuration: claude-opus-4-20250514-thinking-16k
Evaluation type: human preference

1,373.47 rating

Confidence interval: 1,366.96 – 1,379.99

10689 votes

Oct 15, 2026

Category: instruction_following
Evaluated configuration: claude-opus-4-20250514
Evaluation type: human preference

Claude Sonnet 4

1,376.05 rating

Confidence interval: 1,369.03 – 1,383.07

8523 votes

Oct 15, 2026

Category: instruction_following
Evaluated configuration: claude-sonnet-4-20250514-thinking-32k
Evaluation type: human preference

1,351.99 rating

Confidence interval: 1,345.34 – 1,358.65

9910 votes

Oct 15, 2026

Category: instruction_following
Evaluated configuration: claude-sonnet-4-20250514
Evaluation type: human preference

Arena text preference / japanesehuman preference · 2026-10-15 · rating

Claude Opus 4

1,330.92 rating

Confidence interval: 1,309.10 – 1,352.73

831 votes

Oct 15, 2026

Category: japanese
Evaluated configuration: claude-opus-4-20250514-thinking-16k
Evaluation type: human preference

1,329.55 rating

Confidence interval: 1,310.75 – 1,348.35

1115 votes

Oct 15, 2026

Category: japanese
Evaluated configuration: claude-opus-4-20250514
Evaluation type: human preference

Claude Sonnet 4

1,301.65 rating

Confidence interval: 1,281.73 – 1,321.57

969 votes

Oct 15, 2026

Category: japanese
Evaluated configuration: claude-sonnet-4-20250514
Evaluation type: human preference

1,287.13 rating

Confidence interval: 1,264.84 – 1,309.41

821 votes

Oct 15, 2026

Category: japanese
Evaluated configuration: claude-sonnet-4-20250514-thinking-32k
Evaluation type: human preference

Arena text preference / koreanhuman preference · 2026-10-15 · rating

Claude Opus 4

1,321.46 rating

Confidence interval: 1,299.42 – 1,343.50

794 votes

Oct 15, 2026

Category: korean
Evaluated configuration: claude-opus-4-20250514-thinking-16k
Evaluation type: human preference

1,303.29 rating

Confidence interval: 1,283.79 – 1,322.80

1030 votes

Oct 15, 2026

Category: korean
Evaluated configuration: claude-opus-4-20250514
Evaluation type: human preference

Claude Sonnet 4

1,290.73 rating

Confidence interval: 1,270.17 – 1,311.29

930 votes

Oct 15, 2026

Category: korean
Evaluated configuration: claude-sonnet-4-20250514
Evaluation type: human preference

1,271.35 rating

Confidence interval: 1,248.47 – 1,294.24

731 votes

Oct 15, 2026

Category: korean
Evaluated configuration: claude-sonnet-4-20250514-thinking-32k
Evaluation type: human preference

Arena text preference / longer_queryhuman preference · 2026-10-15 · rating

Claude Opus 4

1,422.07 rating

Confidence interval: 1,414.43 – 1,429.72

6966 votes

Oct 15, 2026

Category: longer_query
Evaluated configuration: claude-opus-4-20250514-thinking-16k
Evaluation type: human preference

1,401.30 rating

Confidence interval: 1,394.18 – 1,408.42

8381 votes

Oct 15, 2026

Category: longer_query
Evaluated configuration: claude-opus-4-20250514
Evaluation type: human preference

Claude Sonnet 4

1,397.78 rating

Confidence interval: 1,390.10 – 1,405.47

6721 votes

Oct 15, 2026

Category: longer_query
Evaluated configuration: claude-sonnet-4-20250514-thinking-32k
Evaluation type: human preference

1,379.46 rating

Confidence interval: 1,372.18 – 1,386.74

7699 votes

Oct 15, 2026

Category: longer_query
Evaluated configuration: claude-sonnet-4-20250514
Evaluation type: human preference

Arena text preference / mathhuman preference · 2026-10-15 · rating

Claude Opus 4

1,390.87 rating

Confidence interval: 1,378.62 – 1,403.11

2229 votes

Oct 15, 2026

Category: math
Evaluated configuration: claude-opus-4-20250514-thinking-16k
Evaluation type: human preference

1,372.86 rating

Confidence interval: 1,361.74 – 1,383.99

2746 votes

Oct 15, 2026

Category: math
Evaluated configuration: claude-opus-4-20250514
Evaluation type: human preference

Claude Sonnet 4

1,375.07 rating

Confidence interval: 1,362.20 – 1,387.93

2015 votes

Oct 15, 2026

Category: math
Evaluated configuration: claude-sonnet-4-20250514-thinking-32k
Evaluation type: human preference

1,358.99 rating

Confidence interval: 1,347.28 – 1,370.69

2449 votes

Oct 15, 2026

Category: math
Evaluated configuration: claude-sonnet-4-20250514
Evaluation type: human preference

Arena text preference / multi_turnhuman preference · 2026-10-15 · rating

Claude Opus 4

1,395.83 rating

Confidence interval: 1,387.62 – 1,404.05

6044 votes

Oct 15, 2026

Category: multi_turn
Evaluated configuration: claude-opus-4-20250514-thinking-16k
Evaluation type: human preference

1,388.41 rating

Confidence interval: 1,380.75 – 1,396.07

7370 votes

Oct 15, 2026

Category: multi_turn
Evaluated configuration: claude-opus-4-20250514
Evaluation type: human preference

Claude Sonnet 4

1,376.44 rating

Confidence interval: 1,368.08 – 1,384.79

5633 votes

Oct 15, 2026

Category: multi_turn
Evaluated configuration: claude-sonnet-4-20250514-thinking-32k
Evaluation type: human preference

1,364.73 rating

Confidence interval: 1,356.81 – 1,372.64

6816 votes

Oct 15, 2026

Category: multi_turn
Evaluated configuration: claude-sonnet-4-20250514
Evaluation type: human preference

Arena text preference / non_englishhuman preference · 2026-10-15 · rating

Claude Opus 4

1,361.57 rating

Confidence interval: 1,356.25 – 1,366.88

20387 votes

Oct 15, 2026

Category: non_english
Evaluated configuration: claude-opus-4-20250514-thinking-16k
Evaluation type: human preference

1,351.89 rating

Confidence interval: 1,346.73 – 1,357.05

23980 votes

Oct 15, 2026

Category: non_english
Evaluated configuration: claude-opus-4-20250514
Evaluation type: human preference

Claude Sonnet 4

1,332.63 rating

Confidence interval: 1,327.26 – 1,338.00

19280 votes

Oct 15, 2026

Category: non_english
Evaluated configuration: claude-sonnet-4-20250514-thinking-32k
Evaluation type: human preference

1,330.07 rating

Confidence interval: 1,324.76 – 1,335.38

21949 votes

Oct 15, 2026

Category: non_english
Evaluated configuration: claude-sonnet-4-20250514
Evaluation type: human preference

Arena text preference / overallhuman preference · 2026-10-15 · rating

Claude Opus 4

1,377.07 rating

Confidence interval: 1,372.63 – 1,381.50

35904 votes

Oct 15, 2026

Category: overall
Evaluated configuration: claude-opus-4-20250514-thinking-16k
Evaluation type: human preference

1,365.89 rating

Confidence interval: 1,361.56 – 1,370.22

43043 votes

Oct 15, 2026

Category: overall
Evaluated configuration: claude-opus-4-20250514
Evaluation type: human preference

Claude Sonnet 4

1,350.88 rating

Confidence interval: 1,346.39 – 1,355.38

34132 votes

Oct 15, 2026

Category: overall
Evaluated configuration: claude-sonnet-4-20250514-thinking-32k
Evaluation type: human preference

1,339.25 rating

Confidence interval: 1,334.82 – 1,343.67

39163 votes

Oct 15, 2026

Category: overall
Evaluated configuration: claude-sonnet-4-20250514
Evaluation type: human preference

Arena text preference / polishhuman preference · 2026-10-15 · rating

Claude Opus 4

1,355.52 rating

Confidence interval: 1,344.60 – 1,366.45

3572 votes

Oct 15, 2026

Category: polish
Evaluated configuration: claude-opus-4-20250514-thinking-16k
Evaluation type: human preference

1,343.78 rating

Confidence interval: 1,332.46 – 1,355.09

3165 votes

Oct 15, 2026

Category: polish
Evaluated configuration: claude-opus-4-20250514
Evaluation type: human preference

Claude Sonnet 4

1,324.35 rating

Confidence interval: 1,312.98 – 1,335.71

3272 votes

Oct 15, 2026

Category: polish
Evaluated configuration: claude-sonnet-4-20250514-thinking-32k
Evaluation type: human preference

1,321.74 rating

Confidence interval: 1,309.81 – 1,333.68

2915 votes

Oct 15, 2026

Category: polish
Evaluated configuration: claude-sonnet-4-20250514
Evaluation type: human preference

Arena text preference / russianhuman preference · 2026-10-15 · rating

Claude Opus 4

1,391.71 rating

Confidence interval: 1,380.23 – 1,403.18

2553 votes

Oct 15, 2026

Category: russian
Evaluated configuration: claude-opus-4-20250514-thinking-16k
Evaluation type: human preference

1,380.98 rating

Confidence interval: 1,370.76 – 1,391.19

3443 votes

Oct 15, 2026

Category: russian
Evaluated configuration: claude-opus-4-20250514
Evaluation type: human preference

Claude Sonnet 4

1,355.35 rating

Confidence interval: 1,343.50 – 1,367.19

2411 votes

Oct 15, 2026

Category: russian
Evaluated configuration: claude-sonnet-4-20250514-thinking-32k
Evaluation type: human preference

1,352.71 rating

Confidence interval: 1,342.18 – 1,363.25

3214 votes

Oct 15, 2026

Category: russian
Evaluated configuration: claude-sonnet-4-20250514
Evaluation type: human preference

Arena text preference / spanishhuman preference · 2026-10-15 · rating

Claude Opus 4

1,388.38 rating

Confidence interval: 1,367.91 – 1,408.85

860 votes

Oct 15, 2026

Category: spanish
Evaluated configuration: claude-opus-4-20250514-thinking-16k
Evaluation type: human preference

1,356.93 rating

Confidence interval: 1,337.37 – 1,376.50

1001 votes

Oct 15, 2026

Category: spanish
Evaluated configuration: claude-opus-4-20250514
Evaluation type: human preference

Claude Sonnet 4

1,356.67 rating

Confidence interval: 1,335.33 – 1,378.01

835 votes

Oct 15, 2026

Category: spanish
Evaluated configuration: claude-sonnet-4-20250514-thinking-32k
Evaluation type: human preference

1,349.42 rating

Confidence interval: 1,328.86 – 1,369.98

891 votes

Oct 15, 2026

Category: spanish
Evaluated configuration: claude-sonnet-4-20250514
Evaluation type: human preference

* Provisional data