Compare Models
Select models (max 5)
Claude Sonnet 5.5MiMo V2.6 Flash
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | 69.22%±0.96 | 59.58%±1.13 |
| Legal Research BenchAgentic US legal research | 48.08%±3.47 | 37.98%±3.37 |
| Finance Agent (v2)Core financial analyst tasks | 58.10%±0.67 | 56.28%±0.46 |
| Tax Agent BenchAgentic US corporate tax research | 73.39%±2.98 | 59.90%±3.13 |
| MedCodeMedical billing code support | 52.92%±2.12 | 41.06%±2.03 |
| Terminal-Bench ScienceExpert-authored scientific research workflows | 38.57%±5.86 | 5.71%±2.79 |
| Code MigrationRewriting programs in new languages | 69.83%±4.26 | 40.93%±4.35 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 53.03%±1.51 | 21.21%±1.75 |
| Vibe Code Bench v1.1Building web apps from scratch | 92.39%±1.26 | 78.96%±4.04 |
Benchmarks
Vals Index *
Claude Sonnet 5.5
0.00%± 0.96
(66/66)MiMo V2.6 Flash
0.00%± 1.13
(66/66)Legal Research Bench *
Claude Sonnet 5.5
0.00%± 3.47
(69/69)MiMo V2.6 Flash
0.00%± 3.37
(69/69)Finance Agent (v2) *
Claude Sonnet 5.5
0.00%± 0.67
(70/70)MiMo V2.6 Flash
0.00%± 0.46
(70/70)Tax Agent Bench *
Claude Sonnet 5.5
0.00%± 2.98
(61/61)MiMo V2.6 Flash
0.00%± 3.13
(61/61)MedCode *
Claude Sonnet 5.5
0.00%± 2.12
(102/102)MiMo V2.6 Flash
0.00%± 2.03
(102/102)Terminal-Bench Science
Claude Sonnet 5.5
0.00%± 5.86
(33/33)MiMo V2.6 Flash
0.00%± 2.79
(33/33)Code Migration *
Claude Sonnet 5.5
0.00%± 4.26
(69/69)MiMo V2.6 Flash
0.00%± 4.35
(69/69)Terminal-Bench 4.0
Claude Sonnet 5.5
0.00%± 1.51
(37/37)MiMo V2.6 Flash
0.00%± 1.75
(37/37)Vibe Code Bench v1.1 *
Claude Sonnet 5.5
0.00%± 1.26
(104/104)MiMo V2.6 Flash
0.00%± 4.04
(104/104)Overall performance
Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, and law
•2026-09-27
Comparison by Industry
Model performance on different sections of the economy.
Vals Index
69.22%
vs.59.58%
Legal
25.50%
vs.24.62%
Finance
69.07%
vs.60.55%
Healthcare
72.01%
vs.63.17%
Math
100.00%
vs.63.00%
Science
56.26%
vs.32.20%
Education
51.77%
vs.43.53%
Coding
74.58%
vs.37.85%
Beta
44.87%
vs.39.78%
Social Mobility
67.19%
vs.67.59%
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
$20.80
$0.197
Cost / TestVals Index
$20.80
vs.$0.197
Input Cost/ 1M Tokens
$2.00
vs.$0.14
Input Cache Write/ 1M Tokens
$2.50
vs.N/A
Input Cache Read/ 1M Tokens
$0.20
vs.$0.003
Output Cost/ 1M Tokens
$10.00
vs.$0.28
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | Anthropic | Xiaomi |
| Latency | 4207.12s | 2701.77s |
| Cost (In/Out) | $2 / $10 | $0.14 / $0.28 |
| Context Window | 1M | 1M |
| Max Output Token | 128k | 128k |
| Input Modality |