Compare Models
Select models (max 5)
Muse Spark 1.3MiMo V2.6 Flash
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | 53.20%±1.07 | 53.23%±1.10 |
| Legal Research BenchAgentic US legal research | 40.87%±3.42 | 37.98%±3.37 |
| Finance Agent (v2)Core financial analyst tasks | 58.90%±0.44 | 56.28%±0.46 |
| Tax Agent BenchAgentic US corporate tax research | 71.93%±2.92 | 59.90%±3.13 |
| MedCodeMedical billing code support | N/A | 41.06%±2.03 |
| Terminal-Bench ScienceExpert-authored scientific research workflows | 4.29%±2.44 | 4.29%±2.44 |
| Code MigrationRewriting programs in new languages | 27.58%±4.07 | 40.93%±4.35 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 10.61%±1.75 | 24.24%±1.51 |
| Vibe Code Bench v1.1Building web apps from scratch | 82.86%±2.90 | 78.96%±4.04 |
Benchmarks
Vals Index *
Muse Spark 1.3
0.00%± 1.07
(43/43)MiMo V2.6 Flash
0.00%± 1.10
(43/43)Legal Research Bench *
Muse Spark 1.3
0.00%± 3.42
(73/73)MiMo V2.6 Flash
0.00%± 3.37
(73/73)Finance Agent (v2) *
Muse Spark 1.3
0.00%± 0.44
(74/74)MiMo V2.6 Flash
0.00%± 0.46
(74/74)Tax Agent Bench *
Muse Spark 1.3
0.00%± 2.92
(65/65)MiMo V2.6 Flash
0.00%± 3.13
(65/65)MedCode *
Muse Spark 1.3
N/AMiMo V2.6 Flash
0.00%± 2.03
(104/104)Terminal-Bench Science
Muse Spark 1.3
0.00%± 2.44
(38/38)MiMo V2.6 Flash
0.00%± 2.44
(38/38)Code Migration *
Muse Spark 1.3
0.00%± 4.07
(73/73)MiMo V2.6 Flash
0.00%± 4.35
(73/73)Terminal-Bench 4.0
Muse Spark 1.3
0.00%± 1.75
(43/43)MiMo V2.6 Flash
0.00%± 1.51
(43/43)Vibe Code Bench v1.1 *
Muse Spark 1.3
0.00%± 2.90
(108/108)MiMo V2.6 Flash
0.00%± 4.04
(108/108)Overall performance
Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, and law
•2026-10-02
Comparison by Industry
Model performance on different sections of the economy.
Legal
31.89%
vs.24.62%
Finance
64.52%
vs.60.55%
Healthcare
N/A
vs.63.17%
Math
55.00%
vs.63.00%
Science
4.29%
vs.31.72%
Education
N/A
vs.43.53%
Coding
33.10%
vs.38.46%
Cyber
69.41%
vs.39.78%
Social Mobility
N/A
vs.67.59%
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
$3.376
$0.202
Cost / TestVals Index
$3.376
vs.$0.202
Input Cost/ 1M Tokens
$1.25
vs.$0.14
Input Cache Read/ 1M Tokens
$0.15
vs.$0.003
Output Cost/ 1M Tokens
$4.25
vs.$0.28
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | Meta | Xiaomi |
| Latency | 1962.38s | 3481.73s |
| Cost (In/Out) | $1.25 / $4.25 | $0.14 / $0.28 |
| Context Window | 1M | 1M |
| Max Output Token | 131k | 128k |
| Input Modality |