Compare Models

Select models (max 5)
Claude Sonnet 5 (Cyber Range)Muse Spark Open
Benchmarks

Vals Index *

Claude Sonnet 5 (Cyber Range)
N/A
Muse Spark Open
0.00%± 1.20
(49/49)

Legal Research Bench *

Claude Sonnet 5 (Cyber Range)
N/A
Muse Spark Open
0.00%± 3.38
(79/79)

Finance Agent (v2) *

Claude Sonnet 5 (Cyber Range)
N/A
Muse Spark Open
0.00%± 2.09
(79/79)

Tax Agent Bench *

Claude Sonnet 5 (Cyber Range)
N/A
Muse Spark Open
0.00%± 2.65
(70/70)

Code Migration *

Claude Sonnet 5 (Cyber Range)
N/A
Muse Spark Open
0.00%± 3.47
(78/78)

Terminal-Bench 4.0

Claude Sonnet 5 (Cyber Range)
N/A
Muse Spark Open
0.00%± 0.51
(49/49)

Vibe Code Bench v1.1 *

Claude Sonnet 5 (Cyber Range)
N/A
Muse Spark Open
0.00%± 3.32
(113/113)

Overall performance

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

2026-10-16

Comparison by Industry

Model performance on different sections of the economy.

Legal
N/A
27.56%
Finance
N/A
47.11%
Coding
N/A
34.64%
Cyber
70.30%
N/A

Cost Analysis

Per task and per token model pricing.

Vals Index · USD
N/A
$4.077
Cost / TestVals Index
N/A
$4.077
Input Cost/ 1M Tokens
$2.00
$1.25
Input Cache Write/ 1M Tokens
$2.50
N/A
Input Cache Read/ 1M Tokens
$0.20
$0.15
Output Cost/ 1M Tokens
$10.00
$4.25

Model Metadata

Basic information about each model.

Model provider
AnthropicAnthropic
MetaTogether
LatencyN/A4059.60s
Cost (In/Out)$2 / $10$1.25 / $4.25
Context Window1M1M
Max Output Token128k131k
Input Modality