Compare Models
Select models (max 7)
Grok 4.5MiMo V2.5 Pro
 |  |  |
|---|---|---|
| Legal Research BenchAgentic US legal research | 37.98%±3.37 | 15.87%±2.54 |
| Tax Agent BenchAgentic US corporate tax research | 24.86%±3.12 | 11.50%±1.96 |
| MedCodeMedical billing code support | 43.29%±2.31 | 32.48%±1.91 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 8.59%±1.34 | 0.51%±0.51 |
| Vibe Code Bench v1.1Building web apps from scratch | 69.00%±4.48 | 34.11%±4.53 |
Benchmarks
Legal Research Bench *
Grok 4.5
0.00%± 3.37
(84/84)MiMo V2.5 Pro
0.00%± 2.54
(84/84)Tax Agent Bench *
Grok 4.5
0.00%± 3.12
(75/75)MiMo V2.5 Pro
0.00%± 1.96
(75/75)MedCode *
Grok 4.5
0.00%± 2.31
(107/107)MiMo V2.5 Pro
0.00%± 1.91
(107/107)Terminal-Bench 4.0
Grok 4.5
0.00%± 1.34
(54/54)MiMo V2.5 Pro
0.00%± 0.51
(54/54)Vibe Code Bench v1.1 *
Grok 4.5
0.00%± 4.48
(118/118)MiMo V2.5 Pro
0.00%± 4.53
(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
61.97%
vs.46.50%
Finance
52.78%
vs.42.65%
Healthcare
65.09%
vs.58.11%
Math
31.00%
vs.22.00%
Academic
81.31%
vs.83.59%
Education
34.97%
vs.N/A
Coding
51.16%
vs.47.49%
Cyber
35.89%
vs.N/A
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
N/A
N/A
Cost / TestVals Index
N/A
vs.N/A
Input Cost/ 1M Tokens
$2.00
vs.$0.435
Input Cache Read/ 1M Tokens
$0.30
vs.$0.004
Output Cost/ 1M Tokens
$6.00
vs.$0.87
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | SpaceXAI | Xiaomi |
| Latency | N/A | N/A |
| Cost (In/Out) | $2 / $6 | $0.435 / $0.87 |
| Context Window | 500k | 1M |
| Max Output Token | 500k | 128k |
| Input Modality |