Compare Models
Select models (max 5)
Claude Sonnet 5.5Muse Spark 1.3 Max
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | 69.22%±0.96 | 64.53%±1.23 |
| Legal Research BenchAgentic US legal research | 48.08%±3.47 | 55.29%±3.46 |
| Finance Agent (v2)Core financial analyst tasks | 58.10%±0.67 | 59.96%±2.06 |
| Tax Agent BenchAgentic US corporate tax research | 73.39%±2.98 | 72.44%±2.88 |
| MedCodeMedical billing code support | 52.92%±2.12 | N/A |
| Terminal-Bench ScienceExpert-authored scientific research workflows | 38.57%±5.86 | 14.29%±4.21 |
| Code MigrationRewriting programs in new languages | 69.83%±4.26 | 47.41%±4.26 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 53.03%±1.51 | 27.78%±2.20 |
| Vibe Code Bench v1.1Building web apps from scratch | 92.39%±1.26 | 85.86%±2.51 |
Benchmarks
Vals Index *
Claude Sonnet 5.5
0.00%± 0.96
(66/66)Muse Spark 1.3 Max
0.00%± 1.23
(66/66)Legal Research Bench *
Claude Sonnet 5.5
0.00%± 3.47
(69/69)Muse Spark 1.3 Max
0.00%± 3.46
(69/69)Finance Agent (v2) *
Claude Sonnet 5.5
0.00%± 0.67
(70/70)Muse Spark 1.3 Max
0.00%± 2.06
(70/70)Tax Agent Bench *
Claude Sonnet 5.5
0.00%± 2.98
(61/61)Muse Spark 1.3 Max
0.00%± 2.88
(61/61)MedCode *
Claude Sonnet 5.5
0.00%± 2.12
(102/102)Muse Spark 1.3 Max
N/ATerminal-Bench Science
Claude Sonnet 5.5
0.00%± 5.86
(33/33)Muse Spark 1.3 Max
0.00%± 4.21
(33/33)Code Migration *
Claude Sonnet 5.5
0.00%± 4.26
(69/69)Muse Spark 1.3 Max
0.00%± 4.26
(69/69)Terminal-Bench 4.0
Claude Sonnet 5.5
0.00%± 1.51
(37/37)Muse Spark 1.3 Max
0.00%± 2.20
(37/37)Vibe Code Bench v1.1 *
Claude Sonnet 5.5
0.00%± 1.26
(104/104)Muse Spark 1.3 Max
0.00%± 2.51
(104/104)Overall performance
Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, and law
•2026-09-27
Comparison by Industry
Model performance on different sections of the economy.
Vals Index
69.22%
vs.42.08%
Legal
25.50%
vs.39.52%
Finance
69.07%
vs.66.61%
Healthcare
72.01%
vs.N/A
Math
100.00%
vs.58.00%
Science
56.26%
vs.25.16%
Education
51.77%
vs.N/A
Coding
74.58%
vs.47.61%
Beta
44.87%
vs.39.29%
Social Mobility
67.19%
vs.N/A
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
$20.80
$3.404
Cost / TestVals Index
$20.80
vs.$3.404
Input Cost/ 1M Tokens
$2.00
vs.$1.25
Input Cache Write/ 1M Tokens
$2.50
vs.N/A
Input Cache Read/ 1M Tokens
$0.20
vs.$0.15
Output Cost/ 1M Tokens
$10.00
vs.$4.25
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | Anthropic | Meta |
| Latency | 4207.12s | 1230.41s |
| Cost (In/Out) | $2 / $10 | $1.25 / $4.25 |
| Context Window | 1M | 1M |
| Max Output Token | 128k | 131k |
| Input Modality |