Compare Models

Select models (max 7)
Claude Opus 5Muse Spark 1.3 Max
Benchmarks

Legal Research Bench *

Claude Opus 5
0.00%± 3.46
(98/98)
Muse Spark 1.3 Max
0.00%± 3.46
(98/98)

Tax Agent Bench *

Claude Opus 5
0.00%± 3.60
(89/89)
Muse Spark 1.3 Max
0.00%± 3.51
(89/89)

MedCode *

Claude Opus 5
0.00%± 1.99
(107/107)
Muse Spark 1.3 Max
N/A

Terminal-Bench-Science

Claude Opus 5
0.00%± 5.35
(47/47)
Muse Spark 1.3 Max
0.00%± 3.61
(47/47)

Terminal-Bench 4.0

Claude Opus 5
0.00%± 1.34
(68/68)
Muse Spark 1.3 Max
0.00%± 0.51
(68/68)

Vibe Code Bench v1.1 *

Claude Opus 5
0.00%± 3.00
(132/132)
Muse Spark 1.3 Max
0.00%± 2.51
(132/132)

Overall performance

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

2026-11-16

Comparison by Industry

Model performance on different sections of the economy.

Legal
71.13%
60.11%
Finance
64.77%
42.44%
Healthcare
77.28%
N/A
Math
99.00%
58.00%
Science
47.93%
23.02%
Academic
91.64%
N/A
Coding
67.96%
42.56%
Cyber
38.79%
38.28%
Social Mobility
76.93%
71.22%

Cost Analysis

Per task and per token model pricing.

Vals Index · USD
N/A
N/A
Cost / TestVals Index
N/A
N/A
Input Cost/ 1M Tokens
$5.00
$1.25
Input Cache Write/ 1M Tokens
$6.25
N/A
Input Cache Read/ 1M Tokens
$0.50
$0.15
Output Cost/ 1M Tokens
$25.00
$4.25

Model Metadata

Basic information about each model.

Model provider
AnthropicAnthropic
MetaMeta
LatencyN/AN/A
Cost (In/Out)$5 / $25$1.25 / $4.25
Context Window1M1M
Max Output Token128k131k
Input Modality