Compare Models

Select models (max 7)
Claude Opus 4.5 (Thinking)Gemini 4 Carbon
Benchmarks

Vals Index *

Claude Opus 4.5 (Thinking)
N/A
Gemini 4 Carbon
0.00%± 0.97
(29/29)

Legal Research Bench *

Claude Opus 4.5 (Thinking)
N/A
Gemini 4 Carbon
0.00%± 3.45
(87/87)

Finance Agent v2.1 *

Claude Opus 4.5 (Thinking)
N/A
Gemini 4 Carbon
0.00%± 2.02
(33/33)

Tax Agent Bench *

Claude Opus 4.5 (Thinking)
N/A
Gemini 4 Carbon
0.00%± 3.42
(78/78)

MedCode *

Claude Opus 4.5 (Thinking)
0.00%± 2.01
(107/107)
Gemini 4 Carbon
N/A

Terminal-Bench 4.0

Claude Opus 4.5 (Thinking)
N/A
Gemini 4 Carbon
0.00%± 2.20
(57/57)

Vibe Code Bench v1.1 *

Claude Opus 4.5 (Thinking)
0.00%± 3.16
(121/121)
Gemini 4 Carbon
0.00%± 2.29
(121/121)

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
84.60%
36.63%
Finance
71.27%
64.16%
Healthcare
67.24%
N/A
Academic
85.36%
N/A
Coding
60.23%
76.10%

Cost Analysis

Per task and per token model pricing.

Vals Index · USD
N/A
$10.51
Cost / TestVals Index
N/A
$10.51
Input Cost/ 1M Tokens
$5.00
$4.00
Input Cache Write/ 1M Tokens
$6.25
N/A
Input Cache Read/ 1M Tokens
$0.50
$0.20
Output Cost/ 1M Tokens
$25.00
$20.00

Model Metadata

Basic information about each model.

Model provider
AnthropicAnthropic
GoogleGoogle
LatencyN/A2864.86s
Cost (In/Out)$5 / $25$4 / $20
Context Window200k1M
Max Output Token64k1M
Input Modality