Compare Models

Select models (max 7)

Claude Opus 5Wonder Full


Vals IndexGDP-weighted benchmark	N/A	66.79%±1.07
Legal Research BenchAgentic US legal research	55.29%±3.46	53.37%±3.47
Finance Agent v2.1Core financial analyst tasks	N/A	67.58%±1.98
Tax Agent BenchAgentic US corporate tax research	45.55%±3.59	43.00%±3.57
MedCodeMedical billing code support	63.57%±1.99	49.93%±2.18
Terminal-Bench-ScienceExpert-authored scientific research workflows	27.14%±5.35	37.14%±5.82
Code Migration v1.1Rewriting programs in new languages	N/A	62.79%±3.17
Terminal-Bench 4.0Frontier-difficulty terminal tasks	53.53%±1.34	58.08%±3.31
Vibe Code Bench v1.1Building web apps from scratch	88.40%±3.00	86.00%±1.93

Benchmarks

Vals Index *

Claude Opus 5

N/A

Wonder Full

0.00%± 1.07

(26/26)

Legal Research Bench *

Claude Opus 5

0.00%± 3.46

(84/84)

Wonder Full

0.00%± 3.47

(84/84)

Finance Agent v2.1 *

Claude Opus 5

N/A

Wonder Full

0.00%± 1.98

(30/30)

Tax Agent Bench *

Claude Opus 5

0.00%± 3.59

(75/75)

Wonder Full

0.00%± 3.57

(75/75)

MedCode *

Claude Opus 5

0.00%± 1.99

(107/107)

Wonder Full

0.00%± 2.18

(107/107)

Terminal-Bench-Science

Claude Opus 5

0.00%± 5.35

(42/42)

Wonder Full

0.00%± 5.82

(42/42)

Code Migration v1.1 *

Claude Opus 5

N/A

Wonder Full

0.00%± 3.17

(28/28)

Terminal-Bench 4.0

Claude Opus 5

0.00%± 1.34

(54/54)

Wonder Full

0.00%± 3.31

(54/54)

Vibe Code Bench v1.1 *

Claude Opus 5

0.00%± 3.00

(118/118)

Wonder Full

0.00%± 1.93

(118/118)

Overall performance

Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, and law

•2026-10-22

Claude Opus 5 Wonder Full

Comparison by Industry

Model performance on different sections of the economy.

Legal

71.13%

vs.

54.71%

Finance

64.25%

vs.

61.86%

Healthcare

77.28%

vs.

69.63%

Math

99.00%

vs.

94.00%

Science

47.93%

vs.

39.01%

Academic

91.64%

vs.

N/A

Education

49.43%

vs.

N/A

Coding

63.03%

vs.

52.64%

Cyber

38.79%

vs.

42.73%

Social Mobility

76.93%

vs.

73.75%

Cost Analysis

Per task and per token model pricing.

Vals Index · USD

N/A

$6.81

Cost / TestVals Index

N/A

vs.

$6.81

Input Cost/ 1M Tokens

$5.00

vs.

$4.00

Input Cache Write/ 1M Tokens

$6.25

vs.

N/A

Input Cache Read/ 1M Tokens

$0.50

vs.

$0.20

Output Cost/ 1M Tokens

$25.00

vs.

$20.00

Model Metadata

Basic information about each model.


Model provider	Anthropic	Meta
Latency	N/A	3558.57s
Cost (In/Out)	$5 / $25	$4 / $20
Context Window	1M	1M
Max Output Token	128k	131k
Input Modality