Compare Models
Select models (max 7)
Claude Fable 5Drex Max
 |  |  |
|---|---|---|
| Legal Research BenchAgentic US legal research | 49.52%±3.48 | N/A |
| Tax Agent BenchAgentic US corporate tax research | 38.28%±3.50 | N/A |
| MedCodeMedical billing code support | 56.07%±2.20 | N/A |
| Terminal-Bench-ScienceExpert-authored scientific research workflows | 15.71%±4.38 | N/A |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 41.41%±1.34 | N/A |
| Vibe Code Bench v1.1Building web apps from scratch | 90.35%±2.10 | N/A |
Benchmarks
Legal Research Bench *
Claude Fable 5
0.00%± 3.48
(84/84)Drex Max
N/ATax Agent Bench *
Claude Fable 5
0.00%± 3.50
(75/75)Drex Max
N/AMedCode *
Claude Fable 5
0.00%± 2.20
(107/107)Drex Max
N/ATerminal-Bench-Science
Claude Fable 5
0.00%± 4.38
(42/42)Drex Max
N/ATerminal-Bench 4.0
Claude Fable 5
0.00%± 1.34
(54/54)Drex Max
N/AVibe Code Bench v1.1 *
Claude Fable 5
0.00%± 2.10
(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
69.04%
vs.N/A
Finance
61.38%
vs.99.18%
Healthcare
72.30%
vs.N/A
Math
95.00%
vs.N/A
Science
15.71%
vs.N/A
Academic
91.33%
vs.N/A
Education
51.89%
vs.N/A
Coding
63.71%
vs.N/A
Social Mobility
70.43%
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
$10.00
vs.$0.06
Input Cache Write/ 1M Tokens
$12.50
vs.N/A
Input Cache Read/ 1M Tokens
$1.00
vs.N/A
Output Cost/ 1M Tokens
$50.00
vs.$0.00
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | Anthropic | Decision |
| Latency | N/A | N/A |
| Cost (In/Out) | $10 / $50 | $0.06 / $0 |
| Context Window | 1M | 262k |
| Max Output Token | 128k | 0 |
| Input Modality |