Compare Models

Select models (max 7)
Claude Opus 5.5 (CVP)Inkling 2 Mini
Benchmarks

Vals Index *

Claude Opus 5.5 (CVP)
N/A
Inkling 2 Mini
0.00%± 1.11
(43/43)

Legal Research Bench *

Claude Opus 5.5 (CVP)
N/A
Inkling 2 Mini
0.00%± 2.66
(100/100)

Finance Agent v2.1 *

Claude Opus 5.5 (CVP)
N/A
Inkling 2 Mini
0.00%± 2.13
(46/46)

Tax Agent Bench *

Claude Opus 5.5 (CVP)
N/A
Inkling 2 Mini
0.00%± 2.20
(91/91)

MedCode *

Claude Opus 5.5 (CVP)
N/A
Inkling 2 Mini
0.00%± 1.90
(109/109)

Terminal-Bench-Science

Claude Opus 5.5 (CVP)
N/A
Inkling 2 Mini
0.00%± 0.00
(49/49)

Code Migration v1.1 *

Claude Opus 5.5 (CVP)
N/A
Inkling 2 Mini
0.00%± 3.87
(31/31)

Terminal-Bench 4.0

Claude Opus 5.5 (CVP)
N/A
Inkling 2 Mini
0.00%± 0.51
(70/70)

Vibe Code Bench v1.1 *

Claude Opus 5.5 (CVP)
N/A
Inkling 2 Mini
0.00%± 3.76
(134/134)

Overall performance

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

2026-11-19

Only selected models with a Vals Index score are shown.

Comparison by Industry

Model performance on different sections of the economy.

Legal
N/A
11.39%
Finance
N/A
45.56%
Healthcare
N/A
56.04%
Math
N/A
18.00%
Science
N/A
23.58%
Education
N/A
85.89%
Coding
N/A
28.70%
Cyber
48.17%
37.29%

Cost Analysis

Per task and per token model pricing.

Vals Index · USD
N/A
$3.197
Cost / TestVals Index
N/A
$3.197
Input Cost/ 1M Tokens
$4.00
$0.15
Input Cache Write/ 1M Tokens
$5.00
N/A
Input Cache Read/ 1M Tokens
$0.20
$0.03
Output Cost/ 1M Tokens
$20.00
$0.50

Model Metadata

Basic information about each model.

Model provider
AnthropicAnthropic
Thinking MachinesThinking Machines
LatencyN/A2835.36s
Cost (In/Out)$4 / $20$0.15 / $0.5
Context Window1M1M
Max Output Token128k1M
Input Modality