Compare Models
Select models (max 7)
Claude Opus 4.8MiMo V2.6 Flash
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | N/A | 54.83%±1.11 |
| Legal Research BenchAgentic US legal research | 43.75%±3.45 | 37.98%±3.37 |
| Finance Agent v2.1Core financial analyst tasks | N/A | 63.32%±2.08 |
| Tax Agent BenchAgentic US corporate tax research | 30.00%±3.30 | 28.51%±3.14 |
| MedCodeMedical billing code support | 53.22%±2.17 | 41.06%±2.03 |
| Terminal-Bench-ScienceExpert-authored scientific research workflows | 4.29%±2.44 | 4.29%±2.44 |
| Code Migration v1.1Rewriting programs in new languages | N/A | 39.55%±3.54 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 23.23%±1.34 | 24.24%±1.51 |
| Vibe Code Bench v1.1Building web apps from scratch | 82.72%±3.08 | 78.96%±4.04 |
Benchmarks
Vals Index *
Claude Opus 4.8
N/AMiMo V2.6 Flash
0.00%± 1.11
(26/26)Legal Research Bench *
Claude Opus 4.8
0.00%± 3.45
(84/84)MiMo V2.6 Flash
0.00%± 3.37
(84/84)Finance Agent v2.1 *
Claude Opus 4.8
N/AMiMo V2.6 Flash
0.00% ± 2.08
(30/30)Tax Agent Bench *
Claude Opus 4.8
0.00%± 3.30
(75/75)MiMo V2.6 Flash
0.00%± 3.14
(75/75)MedCode *
Claude Opus 4.8
0.00%± 2.17
(107/107)MiMo V2.6 Flash
0.00%± 2.03
(107/107)Terminal-Bench-Science
Claude Opus 4.8
0.00%± 2.44
(42/42)MiMo V2.6 Flash
0.00%± 2.44
(42/42)Code Migration v1.1 *
Claude Opus 4.8
N/AMiMo V2.6 Flash
0.00%± 3.54
(28/28)Terminal-Bench 4.0
Claude Opus 4.8
0.00%± 1.34
(54/54)MiMo V2.6 Flash
0.00%± 1.51
(54/54)Vibe Code Bench v1.1 *
Claude Opus 4.8
0.00%± 3.08
(118/118)MiMo V2.6 Flash
0.00%± 4.04
(118/118)Overall performance
Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, and law
•2026-10-22
Comparison by Industry
Model performance on different sections of the economy.
Legal
63.66%
vs.25.66%
Finance
58.52%
vs.53.57%
Healthcare
69.49%
vs.63.17%
Math
N/A
vs.63.00%
Science
4.29%
vs.31.72%
Academic
89.53%
vs.N/A
Education
54.79%
vs.43.53%
Coding
57.10%
vs.38.18%
Cyber
N/A
vs.39.78%
Social Mobility
68.13%
vs.67.59%
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
N/A
$0.222
Cost / TestVals Index
N/A
vs.$0.222
Input Cost/ 1M Tokens
$5.00
vs.$0.14
Input Cache Write/ 1M Tokens
$6.25
vs.N/A
Input Cache Read/ 1M Tokens
$0.50
vs.$0.003
Output Cost/ 1M Tokens
$25.00
vs.$0.28
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | Anthropic | Xiaomi |
| Latency | N/A | 4027.97s |
| Cost (In/Out) | $5 / $25 | $0.14 / $0.28 |
| Context Window | 1M | 1M |
| Max Output Token | 128k | 128k |
| Input Modality |