Compare Models

Select models (max 7)
Qwen 3.8 MaxMuse Spark 1.2
Benchmarks

Legal Research Bench *

Qwen 3.8 Max
0.00%± 3.47
(84/84)
Muse Spark 1.2
0.00%± 3.45
(84/84)

Tax Agent Bench *

Qwen 3.8 Max
0.00%± 3.37
(75/75)
Muse Spark 1.2
0.00%± 2.75
(75/75)

MedCode *

Qwen 3.8 Max
0.00%± 2.03
(107/107)
Muse Spark 1.2
0.00%± 2.19
(107/107)

Terminal-Bench-Science

Qwen 3.8 Max
0.00%± 4.03
(42/42)
Muse Spark 1.2
N/A

Terminal-Bench 4.0

Qwen 3.8 Max
0.00%± 3.94
(54/54)
Muse Spark 1.2
0.00%± 1.51
(54/54)

Vibe Code Bench v1.1 *

Qwen 3.8 Max
0.00%± 5.36
(118/118)
Muse Spark 1.2
0.00%± 3.31
(118/118)

Overall 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
65.60%
64.51%
Finance
59.41%
59.53%
Healthcare
62.81%
69.70%
Math
58.00%
43.00%
Science
18.37%
64.81%
Academic
90.11%
87.20%
Education
51.25%
47.66%
Coding
48.75%
41.18%
Cyber
28.57%
34.76%
Social Mobility
67.12%
68.47%

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
$2.00
$1.25
Input Cache Write/ 1M Tokens
$2.50
N/A
Input Cache Read/ 1M Tokens
$0.25
$0.15
Output Cost/ 1M Tokens
$6.00
$4.25

Model Metadata

Basic information about each model.

Model provider
AlibabaAlibaba
MetaMeta
LatencyN/AN/A
Cost (In/Out)$2 / $6$1.25 / $4.25
Context Window1M1M
Max Output Token128k131k
Input Modality