Compare Models
Select models (max 7)
Claude Opus 5Drex Max
 |  |  |
|---|---|---|
| Legal Research BenchAgentic US legal research | 55.29%±3.46 | N/A |
| Tax Agent BenchAgentic US corporate tax research | 45.55%±3.59 | N/A |
| MedCodeMedical billing code support | 63.57%±1.99 | N/A |
| Terminal-Bench-ScienceExpert-authored scientific research workflows | 27.14%±5.35 | N/A |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 53.53%±1.34 | N/A |
| Vibe Code Bench v1.1Building web apps from scratch | 88.40%±3.00 | N/A |
Benchmarks
Legal Research Bench *
Claude Opus 5
0.00%± 3.46
(84/84)Drex Max
N/ATax Agent Bench *
Claude Opus 5
0.00%± 3.59
(75/75)Drex Max
N/AMedCode *
Claude Opus 5
0.00%± 1.99
(107/107)Drex Max
N/ATerminal-Bench-Science
Claude Opus 5
0.00%± 5.35
(42/42)Drex Max
N/ATerminal-Bench 4.0
Claude Opus 5
0.00%± 1.34
(54/54)Drex Max
N/AVibe Code Bench v1.1 *
Claude Opus 5
0.00%± 3.00
(118/118)Drex Max
N/AOverall performance
Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, and law
•2026-10-22
Comparison by Industry
Model performance on different sections of the economy.
Legal
71.13%
vs.N/A
Finance
64.25%
vs.99.18%
Healthcare
77.28%
vs.N/A
Math
99.00%
vs.N/A
Science
47.93%
vs.N/A
Academic
91.64%
vs.N/A
Education
49.43%
vs.N/A
Coding
63.03%
vs.N/A
Cyber
38.79%
vs.N/A
Social Mobility
76.93%
vs.N/A
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
N/A
N/A
Cost / TestVals Index
N/A
vs.N/A
Input Cost/ 1M Tokens
$5.00
vs.$0.06
Input Cache Write/ 1M Tokens
$6.25
vs.N/A
Input Cache Read/ 1M Tokens
$0.50
vs.N/A
Output Cost/ 1M Tokens
$25.00
vs.$0.00
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | Anthropic | Decision |
| Latency | N/A | N/A |
| Cost (In/Out) | $5 / $25 | $0.06 / $0 |
| Context Window | 1M | 262k |
| Max Output Token | 128k | 0 |
| Input Modality |