Compare Models
Select models (max 5)
DeepSeek V4MiMo V2.5 Pro
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | 38.63%±1.16 | 33.84%±1.17 |
| Legal Research BenchAgentic US legal research | 23.08%±2.93 | 15.87%±2.54 |
| Finance Agent (v2)Core financial analyst tasks | 44.08%±0.65 | 41.50%±1.19 |
| Tax Agent BenchAgentic US corporate tax research | 58.50%±3.13 | 34.79%±2.62 |
| MedCodeMedical billing code support | 40.45%±2.12 | 32.48%±1.91 |
| Code MigrationRewriting programs in new languages | 26.20%±4.04 | 21.56%±4.13 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 11.11%±1.34 | 0.51%±0.51 |
| Vibe Code Bench v1.1Building web apps from scratch | 49.93%±4.77 | 34.11%±4.53 |
Benchmarks
Vals Index *
DeepSeek V4
0.00%± 1.16
(43/43)MiMo V2.5 Pro
0.00%± 1.17
(43/43)Legal Research Bench *
DeepSeek V4
0.00%± 2.93
(73/73)MiMo V2.5 Pro
0.00%± 2.54
(73/73)Finance Agent (v2) *
DeepSeek V4
0.00%± 0.65
(74/74)MiMo V2.5 Pro
0.00%± 1.19
(74/74)Tax Agent Bench *
DeepSeek V4
0.00%± 3.13
(65/65)MiMo V2.5 Pro
0.00%± 2.62
(65/65)MedCode *
DeepSeek V4
0.00%± 2.12
(104/104)MiMo V2.5 Pro
0.00%± 1.91
(104/104)Code Migration *
DeepSeek V4
0.00%± 4.04
(73/73)MiMo V2.5 Pro
0.00%± 4.13
(73/73)Terminal-Bench 4.0
DeepSeek V4
0.00%± 1.34
(43/43)MiMo V2.5 Pro
0.00%± 0.51
(43/43)Vibe Code Bench v1.1 *
DeepSeek V4
0.00%± 4.77
(108/108)MiMo V2.5 Pro
0.00%± 4.53
(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
35.72%
vs.31.69%
Finance
56.57%
vs.51.33%
Healthcare
57.80%
vs.58.11%
Math
16.00%
vs.22.00%
Academic
88.32%
vs.83.59%
Coding
43.34%
vs.42.31%
Social Mobility
62.92%
vs.N/A
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
$1.306
$0.162
Cost / TestVals Index
$1.306
vs.$0.162
Input Cost/ 1M Tokens
$1.32
vs.$0.435
Input Cache Read/ 1M Tokens
$0.044
vs.$0.004
Output Cost/ 1M Tokens
$3.96
vs.$0.87
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | DeepSeek | Xiaomi |
| Latency | 1928.91s | 2073.11s |
| Cost (In/Out) | $1.32 / $3.96 | $0.435 / $0.87 |
| Context Window | 1M | 1M |
| Max Output Token | 384k | 128k |
| Input Modality |