Compare Models

Select models (max 7)
Claude Opus 4.5 (Nonthinking)GPT-6.1 Terra
Benchmarks

Vals Index *

Claude Opus 4.5 (Nonthinking)
N/A
GPT-6.1 Terra
0.00%± 1.03
(28/28)

Legal Research Bench *

Claude Opus 4.5 (Nonthinking)
N/A
GPT-6.1 Terra
0.00%± 3.05
(86/86)

Finance Agent v2.1 *

Claude Opus 4.5 (Nonthinking)
N/A
GPT-6.1 Terra
0.00%± 2.09
(32/32)

Tax Agent Bench *

Claude Opus 4.5 (Nonthinking)
N/A
GPT-6.1 Terra
0.00%± 2.43
(77/77)

MedCode *

Claude Opus 4.5 (Nonthinking)
0.00%± 1.89
(107/107)
GPT-6.1 Terra
N/A

Terminal-Bench 4.0

Claude Opus 4.5 (Nonthinking)
N/A
GPT-6.1 Terra
0.00%± 1.82
(56/56)

Vibe Code Bench v1.1 *

Claude Opus 4.5 (Nonthinking)
N/A
GPT-6.1 Terra
0.00%± 2.87
(120/120)

Overall performance

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

2026-10-27

Comparison by Industry

Model performance on different sections of the economy.

Legal
82.84%
13.81%
Finance
71.50%
48.15%
Healthcare
64.21%
N/A
Academic
82.08%
N/A
Education
45.00%
N/A
Coding
75.03%
66.75%

Cost Analysis

Per task and per token model pricing.

Vals Index · USD
N/A
$2.925
Cost / TestVals Index
N/A
$2.925
Input Cost/ 1M Tokens
$5.00
$1.00
Input Cache Write/ 1M Tokens
$6.25
$1.25
Input Cache Read/ 1M Tokens
$0.50
$0.05
Output Cost/ 1M Tokens
$25.00
$5.00

Model Metadata

Basic information about each model.

Model provider
AnthropicAnthropic
OpenAIOpenAI
LatencyN/A2381.41s
Cost (In/Out)$5 / $25$1 / $5
Context Window200k1M
Max Output Token64k128k
Input Modality