Compare Models
Select models (max 7)
MiMo V2.6 FlashInkling 2 Small
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | 54.83%±1.11 | 56.08%±1.18 |
| Legal Research BenchAgentic US legal research | 37.98%±3.37 | 46.63%±3.47 |
| Finance Agent v2.1Core financial analyst tasks | 63.32%±2.08 | 67.54%±2.02 |
| Tax Agent BenchAgentic US corporate tax research | 28.51%±3.14 | 38.91%±3.27 |
| MedCodeMedical billing code support | 41.06%±2.03 | N/A |
| Terminal-Bench-ScienceExpert-authored scientific research workflows | 4.29%±2.44 | 2.86%±2.01 |
| Code Migration v1.1Rewriting programs in new languages | 39.55%±3.54 | N/A |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 24.24%±1.51 | 12.63%±3.07 |
| Vibe Code Bench v1.1Building web apps from scratch | 78.96%±4.04 | 81.55%±3.45 |
Benchmarks
Vals Index *
MiMo V2.6 Flash
0.00%± 1.11
(34/34)Inkling 2 Small
0.00%± 1.18
(34/34)Legal Research Bench *
MiMo V2.6 Flash
0.00%± 3.37
(91/91)Inkling 2 Small
0.00%± 3.47
(91/91)Finance Agent v2.1 *
MiMo V2.6 Flash
0.00%± 2.08
(37/37)Inkling 2 Small
0.00%± 2.02
(37/37)Tax Agent Bench *
MiMo V2.6 Flash
0.00%± 3.14
(82/82)Inkling 2 Small
0.00%± 3.27
(82/82)MedCode *
MiMo V2.6 Flash
0.00%± 2.03
(107/107)Inkling 2 Small
N/ATerminal-Bench-Science
MiMo V2.6 Flash
0.00%± 2.44
(44/44)Inkling 2 Small
0.00%± 2.01
(44/44)Code Migration v1.1 *
MiMo V2.6 Flash
0.00%± 3.54
(29/29)Inkling 2 Small
N/ATerminal-Bench 4.0
MiMo V2.6 Flash
0.00%± 1.51
(61/61)Inkling 2 Small
0.00%± 3.07
(61/61)Vibe Code Bench v1.1 *
MiMo V2.6 Flash
0.00%± 4.04
(125/125)Inkling 2 Small
0.00%± 3.45
(125/125)Overall performance
Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, legal, and tax
•2026-11-05
Comparison by Industry
Model performance on different sections of the economy.
Legal
25.66%
vs.34.15%
Finance
53.57%
vs.58.65%
Healthcare
63.17%
vs.N/A
Math
63.00%
vs.N/A
Science
31.72%
vs.36.43%
Education
83.26%
vs.88.57%
Coding
38.18%
vs.34.45%
Cyber
39.78%
vs.37.32%
Social Mobility
67.59%
vs.N/A
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
$0.221
$3.509
Cost / TestVals Index
$0.221
vs.$3.509
Input Cost/ 1M Tokens
$0.14
vs.$0.30
Input Cache Read/ 1M Tokens
$0.003
vs.$0.03
Output Cost/ 1M Tokens
$0.28
vs.$1.00
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | Xiaomi | Thinking Machines |
| Latency | 4027.97s | 3034.53s |
| Cost (In/Out) | $0.14 / $0.28 | $0.3 / $1 |
| Context Window | 1M | 1M |
| Max Output Token | 128k | 1M |
| Input Modality |