geekradar
Int
Explore GeekRadar

More to explore

Good gear All topics About us Say hello
GeekRadar / The comparison desk
COMPARE.
AI models
anthropic

Claude Opus 4.1

AI model Released

Context window
200,000 tokens
Maximum output
32,000 tokens
Open weights
No

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 1418.6 claude-opus-4-1-20250805 · 95% interval 1415.7–1421.6 · 77,238 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 4.1

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 4.1 Not available

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 4.1 21.0*% Approx. 95% interval: 13.0–29.0%

Advanced mathematics

FrontierMath Tiers 1-3 · 25%

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

Claude Opus 4.1 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 4.1 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.

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

1,427.04 rating

Confidence interval: 1,418.97 – 1,435.11

5945 votes

Category
chinese
Evaluated configuration
claude-opus-4-1-20250805
Evaluation type
human preference

1,425.38 rating

Confidence interval: 1,415.60 – 1,435.15

3875 votes

Category
chinese
Evaluated configuration
claude-opus-4-1-20250805-thinking-16k
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating

Claude Opus 4.1

1,478.74 rating

Confidence interval: 1,472.31 – 1,485.17

9919 votes

Category
coding
Evaluated configuration
claude-opus-4-1-20250805-thinking-16k
Evaluation type
human preference

1,472.72 rating

Confidence interval: 1,467.38 – 1,478.07

15695 votes

Category
coding
Evaluated configuration
claude-opus-4-1-20250805
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating

Claude Opus 4.1

1,411.87 rating

Confidence interval: 1,404.22 – 1,419.51

6868 votes

Category
creative_writing
Evaluated configuration
claude-opus-4-1-20250805-thinking-16k
Evaluation type
human preference

1,410.48 rating

Confidence interval: 1,404.26 – 1,416.69

10875 votes

Category
creative_writing
Evaluated configuration
claude-opus-4-1-20250805
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating

Claude Opus 4.1

1,432.63 rating

Confidence interval: 1,427.85 – 1,437.41

20907 votes

Category
english
Evaluated configuration
claude-opus-4-1-20250805-thinking-16k
Evaluation type
human preference

1,426.48 rating

Confidence interval: 1,422.38 – 1,430.59

32163 votes

Category
english
Evaluated configuration
claude-opus-4-1-20250805
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating

Claude Opus 4.1

1,406.99 rating

Confidence interval: 1,402.27 – 1,411.71

35616 votes

Category
exclude_ties
Evaluated configuration
claude-opus-4-1-20250805-thinking-16k
Evaluation type
human preference

1,405.54 rating

Confidence interval: 1,401.48 – 1,409.60

55572 votes

Category
exclude_ties
Evaluated configuration
claude-opus-4-1-20250805
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-15 · rating

Claude Opus 4.1

1,438.37 rating

Confidence interval: 1,426.60 – 1,450.14

2539 votes

Category
expert
Evaluated configuration
claude-opus-4-1-20250805-thinking-16k
Evaluation type
human preference

1,425.43 rating

Confidence interval: 1,416.19 – 1,434.67

4229 votes

Category
expert
Evaluated configuration
claude-opus-4-1-20250805
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating

Claude Opus 4.1

1,431.73 rating

Confidence interval: 1,410.65 – 1,452.81

853 votes

Category
french
Evaluated configuration
claude-opus-4-1-20250805-thinking-16k
Evaluation type
human preference

1,427.45 rating

Confidence interval: 1,410.82 – 1,444.08

1416 votes

Category
french
Evaluated configuration
claude-opus-4-1-20250805
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating

Claude Opus 4.1

1,412.56 rating

Confidence interval: 1,393.84 – 1,431.29

1049 votes

Category
german
Evaluated configuration
claude-opus-4-1-20250805-thinking-16k
Evaluation type
human preference

1,404.86 rating

Confidence interval: 1,389.39 – 1,420.32

1567 votes

Category
german
Evaluated configuration
claude-opus-4-1-20250805
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating

Claude Opus 4.1

1,442.33 rating

Confidence interval: 1,437.80 – 1,446.87

24954 votes

Category
hard_prompts
Evaluated configuration
claude-opus-4-1-20250805-thinking-16k
Evaluation type
human preference

1,442.14 rating

Confidence interval: 1,438.28 – 1,446.01

39442 votes

Category
hard_prompts
Evaluated configuration
claude-opus-4-1-20250805
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating

Claude Opus 4.1

1,450.98 rating

Confidence interval: 1,444.83 – 1,457.13

10730 votes

Category
hard_prompts_english
Evaluated configuration
claude-opus-4-1-20250805-thinking-16k
Evaluation type
human preference

1,447.84 rating

Confidence interval: 1,442.60 – 1,453.07

16447 votes

Category
hard_prompts_english
Evaluated configuration
claude-opus-4-1-20250805
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating

Claude Opus 4.1

1,405.65 rating

Confidence interval: 1,400.06 – 1,411.24

14066 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
claude-opus-4-1-20250805
Evaluation type
human preference

1,404.96 rating

Confidence interval: 1,398.36 – 1,411.56

9094 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
claude-opus-4-1-20250805-thinking-16k
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating

Claude Opus 4.1

1,398.42 rating

Confidence interval: 1,392.88 – 1,403.95

14236 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
claude-opus-4-1-20250805
Evaluation type
human preference

1,396.60 rating

Confidence interval: 1,390.00 – 1,403.21

9090 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
claude-opus-4-1-20250805-thinking-16k
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating

Claude Opus 4.1

1,420.42 rating

Confidence interval: 1,409.95 – 1,430.89

3214 votes

Category
industry_legal_and_government
Evaluated configuration
claude-opus-4-1-20250805-thinking-16k
Evaluation type
human preference

1,417.42 rating

Confidence interval: 1,409.01 – 1,425.82

5338 votes

Category
industry_legal_and_government
Evaluated configuration
claude-opus-4-1-20250805
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating

Claude Opus 4.1

1,421.97 rating

Confidence interval: 1,414.97 – 1,428.98

7937 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
claude-opus-4-1-20250805-thinking-16k
Evaluation type
human preference

1,416.90 rating

Confidence interval: 1,411.06 – 1,422.74

12270 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
claude-opus-4-1-20250805
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating

Claude Opus 4.1

1,433.76 rating

Confidence interval: 1,422.20 – 1,445.33

2485 votes

Category
industry_mathematical
Evaluated configuration
claude-opus-4-1-20250805-thinking-16k
Evaluation type
human preference

1,425.79 rating

Confidence interval: 1,416.41 – 1,435.16

3909 votes

Category
industry_mathematical
Evaluated configuration
claude-opus-4-1-20250805
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating

Claude Opus 4.1

1,415.60 rating

Confidence interval: 1,404.06 – 1,427.14

2705 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
claude-opus-4-1-20250805-thinking-16k
Evaluation type
human preference

1,412.92 rating

Confidence interval: 1,403.57 – 1,422.27

4432 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
claude-opus-4-1-20250805
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating

Claude Opus 4.1

1,456.32 rating

Confidence interval: 1,451.09 – 1,461.54

16728 votes

Category
industry_software_and_it_services
Evaluated configuration
claude-opus-4-1-20250805-thinking-16k
Evaluation type
human preference

1,451.62 rating

Confidence interval: 1,447.18 – 1,456.07

26055 votes

Category
industry_software_and_it_services
Evaluated configuration
claude-opus-4-1-20250805
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating

Claude Opus 4.1

1,418.05 rating

Confidence interval: 1,412.89 – 1,423.21

17469 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
claude-opus-4-1-20250805
Evaluation type
human preference

1,417.89 rating

Confidence interval: 1,411.70 – 1,424.08

11060 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
claude-opus-4-1-20250805-thinking-16k
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating

Claude Opus 4.1

1,435.37 rating

Confidence interval: 1,429.64 – 1,441.10

13208 votes

Category
instruction_following
Evaluated configuration
claude-opus-4-1-20250805-thinking-16k
Evaluation type
human preference

1,433.63 rating

Confidence interval: 1,428.80 – 1,438.45

20779 votes

Category
instruction_following
Evaluated configuration
claude-opus-4-1-20250805
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating

Claude Opus 4.1

1,377.49 rating

Confidence interval: 1,355.06 – 1,399.91

674 votes

Category
japanese
Evaluated configuration
claude-opus-4-1-20250805-thinking-16k
Evaluation type
human preference

1,374.36 rating

Confidence interval: 1,356.61 – 1,392.11

1198 votes

Category
japanese
Evaluated configuration
claude-opus-4-1-20250805
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating

Claude Opus 4.1

1,380.43 rating

Confidence interval: 1,361.82 – 1,399.04

1103 votes

Category
korean
Evaluated configuration
claude-opus-4-1-20250805-thinking-16k
Evaluation type
human preference

1,364.08 rating

Confidence interval: 1,348.51 – 1,379.66

1613 votes

Category
korean
Evaluated configuration
claude-opus-4-1-20250805
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating

Claude Opus 4.1

1,454.81 rating

Confidence interval: 1,448.75 – 1,460.86

11485 votes

Category
longer_query
Evaluated configuration
claude-opus-4-1-20250805-thinking-16k
Evaluation type
human preference

1,444.18 rating

Confidence interval: 1,439.13 – 1,449.23

18482 votes

Category
longer_query
Evaluated configuration
claude-opus-4-1-20250805
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating

Claude Opus 4.1

1,430.97 rating

Confidence interval: 1,420.48 – 1,441.46

3059 votes

Category
math
Evaluated configuration
claude-opus-4-1-20250805-thinking-16k
Evaluation type
human preference

1,421.79 rating

Confidence interval: 1,413.30 – 1,430.27

4806 votes

Category
math
Evaluated configuration
claude-opus-4-1-20250805
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating

Claude Opus 4.1

1,444.10 rating

Confidence interval: 1,437.27 – 1,450.94

8468 votes

Category
multi_turn
Evaluated configuration
claude-opus-4-1-20250805-thinking-16k
Evaluation type
human preference

1,443.15 rating

Confidence interval: 1,437.36 – 1,448.94

13115 votes

Category
multi_turn
Evaluated configuration
claude-opus-4-1-20250805
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating

Claude Opus 4.1

1,405.56 rating

Confidence interval: 1,401.88 – 1,409.24

45037 votes

Category
non_english
Evaluated configuration
claude-opus-4-1-20250805
Evaluation type
human preference

1,403.70 rating

Confidence interval: 1,399.40 – 1,408.00

28591 votes

Category
non_english
Evaluated configuration
claude-opus-4-1-20250805-thinking-16k
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating

Claude Opus 4.1

1,419.20 rating

Confidence interval: 1,415.74 – 1,422.66

49542 votes

Category
overall
Evaluated configuration
claude-opus-4-1-20250805-thinking-16k
Evaluation type
human preference

1,418.65 rating

Confidence interval: 1,415.67 – 1,421.62

77238 votes

Category
overall
Evaluated configuration
claude-opus-4-1-20250805
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-10-15 · rating

Claude Opus 4.1

1,413.00 rating

Confidence interval: 1,402.79 – 1,423.22

3733 votes

Category
polish
Evaluated configuration
claude-opus-4-1-20250805
Evaluation type
human preference

1,408.25 rating

Confidence interval: 1,395.78 – 1,420.72

2408 votes

Category
polish
Evaluated configuration
claude-opus-4-1-20250805-thinking-16k
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating

Claude Opus 4.1

1,421.82 rating

Confidence interval: 1,414.70 – 1,428.95

7233 votes

Category
russian
Evaluated configuration
claude-opus-4-1-20250805
Evaluation type
human preference

1,416.74 rating

Confidence interval: 1,407.76 – 1,425.72

4220 votes

Category
russian
Evaluated configuration
claude-opus-4-1-20250805-thinking-16k
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating

Claude Opus 4.1

1,448.24 rating

Confidence interval: 1,434.93 – 1,461.55

2301 votes

Category
spanish
Evaluated configuration
claude-opus-4-1-20250805
Evaluation type
human preference

1,445.35 rating

Confidence interval: 1,428.03 – 1,462.66

1294 votes

Category
spanish
Evaluated configuration
claude-opus-4-1-20250805-thinking-16k
Evaluation type
human preference

Run it locally

Inference · memory estimate

Claude Opus 4.1

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

API cost

USD / month

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

Claude Opus 4.1

Claude Opus 4.1 / Pricing tiers 1
Provider / scopeRateCurrencyAmount / unit
AWS BedrockClaude Opus 4.1Standard Global cross-region Cached inputUSD1.5 / 1M tokens
InputUSD15 / 1M tokens
OutputUSD75 / 1M tokens

Capabilities

Context window
200,000 tokens
Maximum output
32,000 tokens
Reasoning
Yes
Tool calling
Yes
Open weights
No
Knowledge cutoff
2025-03-31
Model license
Proprietary

Input modalities

  • text
  • image
  • pdf

Output modalities

  • text

* Provisional data