Compare Models
Select models (max 7)
Muse Spark 1.3 MaxMiMo V2.6 Pro
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | N/A | 57.81%±1.24 |
| Legal Research BenchAgentic US legal research | 55.29%±3.46 | 47.12%±3.47 |
| Finance Agent v2.1Core financial analyst tasks | N/A | 64.26%±2.02 |
| Tax Agent BenchAgentic US corporate tax research | 42.44%±3.51 | 32.39%±3.36 |
| MedCodeMedical billing code support | N/A | 44.97%±2.10 |
| Terminal-Bench-ScienceExpert-authored scientific research workflows | 10.00%±3.61 | 2.86%±2.01 |
| Code Migration v1.1Rewriting programs in new languages | N/A | 48.79%±3.88 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 24.75%±0.51 | 31.31%±3.07 |
| Vibe Code Bench v1.1Building web apps from scratch | 85.86%±2.51 | 85.22%±3.39 |
Benchmarks
Vals Index *
Muse Spark 1.3 Max
N/AMiMo V2.6 Pro
0.00%± 1.24
(24/24)Legal Research Bench *
Muse Spark 1.3 Max
0.00%± 3.46
(82/82)MiMo V2.6 Pro
0.00%± 3.47
(82/82)Finance Agent v2.1 *
Muse Spark 1.3 Max
N/AMiMo V2.6 Pro
0.00%± 2.02
(28/28)Tax Agent Bench *
Muse Spark 1.3 Max
0.00%± 3.51
(73/73)MiMo V2.6 Pro
0.00%± 3.36
(73/73)MedCode *
Muse Spark 1.3 Max
N/AMiMo V2.6 Pro
0.00%± 2.10
(107/107)Terminal-Bench-Science
Muse Spark 1.3 Max
0.00%± 3.61
(42/42)MiMo V2.6 Pro
0.00%± 2.01
(42/42)Code Migration v1.1 *
Muse Spark 1.3 Max
N/AMiMo V2.6 Pro
0.00%± 3.88
(26/26)Terminal-Bench 4.0
Muse Spark 1.3 Max
0.00%± 0.51
(52/52)MiMo V2.6 Pro
0.00%± 3.07
(52/52)Vibe Code Bench v1.1 *
Muse Spark 1.3 Max
0.00%± 2.51
(116/116)MiMo V2.6 Pro
0.00%± 3.39
(116/116)Overall performance
Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, and law
•2026-10-21
Comparison by Industry
Model performance on different sections of the economy.
Legal
55.29%
vs.30.43%
Finance
42.44%
vs.54.66%
Healthcare
N/A
vs.66.64%
Math
58.00%
vs.70.00%
Science
23.02%
vs.9.09%
Education
N/A
vs.45.05%
Coding
38.87%
vs.41.07%
Cyber
38.28%
vs.37.95%
Social Mobility
N/A
vs.68.94%
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
N/A
$0.435
Cost / TestVals Index
N/A
vs.$0.435
Input Cost/ 1M Tokens
$1.25
vs.$0.435
Input Cache Read/ 1M Tokens
$0.15
vs.$0.004
Output Cost/ 1M Tokens
$4.25
vs.$0.87
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | Meta | Xiaomi |
| Latency | N/A | 4355.89s |
| Cost (In/Out) | $1.25 / $4.25 | $0.435 / $0.87 |
| Context Window | 1M | 1M |
| Max Output Token | 131k | 128k |
| Input Modality |