Compare Models
Select models (max 7)
Claude Fable 5.2Muse Ember
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | 71.31%±0.96 | 60.48%±1.07 |
| Legal Research BenchAgentic US legal research | 46.15%±3.46 | 49.04%±3.48 |
| Finance Agent v2.1Core financial analyst tasks | 69.47%±1.98 | 63.83%±2.01 |
| Tax Agent BenchAgentic US corporate tax research | 32.09%±3.37 | 38.23%±3.50 |
| Terminal-Bench-ScienceExpert-authored scientific research workflows | 55.71%±5.98 | N/A |
| Code Migration v1.1Rewriting programs in new languages | 83.27%±3.12 | N/A |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 65.15%±2.31 | 39.39%±2.31 |
| Vibe Code Bench v1.1Building web apps from scratch | 93.77%±1.15 | 83.70%±2.76 |
Benchmarks
Vals Index *
Claude Fable 5.2
0.00%± 0.96
(36/36)Muse Ember
0.00%± 1.07
(36/36)Legal Research Bench *
Claude Fable 5.2
0.00%± 3.46
(93/93)Muse Ember
0.00%± 3.48
(93/93)Finance Agent v2.1 *
Claude Fable 5.2
0.00%± 1.98
(39/39)Muse Ember
0.00%± 2.01
(39/39)Tax Agent Bench *
Claude Fable 5.2
0.00%± 3.37
(84/84)Muse Ember
0.00%± 3.50
(84/84)Terminal-Bench-Science
Claude Fable 5.2
0.00%± 5.98
(45/45)Muse Ember
N/ACode Migration v1.1 *
Claude Fable 5.2
0.00%± 3.12
(30/30)Muse Ember
N/ATerminal-Bench 4.0
Claude Fable 5.2
0.00%± 2.31
(63/63)Muse Ember
0.00%± 2.31
(63/63)Vibe Code Bench v1.1 *
Claude Fable 5.2
0.00%± 1.15
(127/127)Muse Ember
0.00%± 2.76
(127/127)Overall performance
Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, legal, and tax
•2026-11-09
Comparison by Industry
Model performance on different sections of the economy.
Legal
41.71%
vs.37.02%
Finance
59.65%
vs.58.08%
Math
100.00%
vs.N/A
Science
63.74%
vs.N/A
Coding
64.70%
vs.61.55%
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
$17.94
$0.153
Cost / TestVals Index
$17.94
vs.$0.153
Input Cost/ 1M Tokens
$8.00
vs.$0.10
Input Cache Write/ 1M Tokens
$10.00
vs.N/A
Input Cache Read/ 1M Tokens
$0.20
vs.$0.004
Output Cost/ 1M Tokens
$40.00
vs.$0.50
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | Anthropic | Meta |
| Latency | 2621.82s | 902.37s |
| Cost (In/Out) | $8 / $40 | $0.1 / $0.5 |
| Context Window | 1M | 1M |
| Max Output Token | 128k | 524k |
| Input Modality |