Compare Models

Select models (max 7)

Claude Sonnet 5.5Wonder


Vals IndexGDP-weighted benchmark	70.85%±0.93	64.88%±1.07
Legal Research BenchAgentic US legal research	48.08%±3.47	50.48%±3.48
Finance Agent v2.1Core financial analyst tasks	67.28%±2.02	65.55%±2.03
Tax Agent BenchAgentic US corporate tax research	41.96%±3.56	36.27%±3.47
MedCodeMedical billing code support	52.92%±2.12	N/A
Terminal-Bench-ScienceExpert-authored scientific research workflows	47.14%±6.01	22.86%±5.05
Code Migration v1.1Rewriting programs in new languages	86.88%±1.52	72.36%±3.19
Terminal-Bench 4.0Frontier-difficulty terminal tasks	64.14%±1.01	49.49%±2.20
Vibe Code Bench v1.1Building web apps from scratch	92.39%±1.26	83.09%±2.49

Benchmarks

Vals Index *

Claude Sonnet 5.5

0.00%± 0.93

(26/26)

Wonder

0.00%± 1.07

(26/26)

Legal Research Bench *

Claude Sonnet 5.5

0.00%± 3.47

(84/84)

Wonder

0.00%± 3.48

(84/84)

Finance Agent v2.1 *

Claude Sonnet 5.5

0.00%± 2.02

(30/30)

Wonder

0.00%± 2.03

(30/30)

Tax Agent Bench *

Claude Sonnet 5.5

0.00%± 3.56

(75/75)

Wonder

0.00%± 3.47

(75/75)

MedCode *

Claude Sonnet 5.5

0.00%± 2.12

(107/107)

Wonder

N/A

Terminal-Bench-Science

Claude Sonnet 5.5

0.00%± 6.01

(42/42)

Wonder

0.00%± 5.05

(42/42)

Code Migration v1.1 *

Claude Sonnet 5.5

0.00%± 1.52

(28/28)

Wonder

0.00%± 3.19

(28/28)

Terminal-Bench 4.0

Claude Sonnet 5.5

0.00%± 1.01

(54/54)

Wonder

0.00%± 2.20

(54/54)

Vibe Code Bench v1.1 *

Claude Sonnet 5.5

0.00%± 1.26

(118/118)

Wonder

0.00%± 2.49

(118/118)

Overall performance

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

•2026-10-22

Claude Sonnet 5.5 Wonder

Comparison by Industry

Model performance on different sections of the economy.

Legal

29.25%

vs.

37.12%

Finance

71.28%

vs.

58.11%

Healthcare

72.01%

vs.

N/A

Math

100.00%

vs.

84.00%

Science

59.12%

vs.

39.12%

Education

51.77%

vs.

N/A

Coding

65.22%

vs.

57.34%

Cyber

44.87%

vs.

80.36%

Social Mobility

67.19%

vs.

70.23%

Cost Analysis

Per task and per token model pricing.

Vals Index · USD

$18.70

$10.65

Cost / TestVals Index

$18.70

vs.

$10.65

Input Cost/ 1M Tokens

$2.00

vs.

$4.00

Input Cache Write/ 1M Tokens

$2.50

vs.

N/A

Input Cache Read/ 1M Tokens

$0.10

vs.

$0.20

Output Cost/ 1M Tokens

$10.00

vs.

$20.00

Model Metadata

Basic information about each model.


Model provider	Anthropic	Meta
Latency	5158.77s	2123.57s
Cost (In/Out)	$2 / $10	$4 / $20
Context Window	1M	1M
Max Output Token	128k	131k
Input Modality