Compare Models
Select models (max 5)
MiMo V2.5GLM 5.3 Flash
 |  |  |
|---|---|---|
| Legal Research BenchAgentic US legal research | 9.13%±2.00 | 45.19%±3.46 |
| Finance Agent (v2)Core financial analyst tasks | 36.73%±0.11 | 57.85%±2.06 |
| Tax Agent BenchAgentic US corporate tax research | 29.16%±2.71 | 61.96%±3.26 |
| MedCodeMedical billing code support | 31.89%±2.02 | N/A |
| Terminal-Bench ScienceExpert-authored scientific research workflows | N/A | 2.86%±2.01 |
| Code MigrationRewriting programs in new languages | 14.23%±3.69 | 20.52%±4.21 |
| Vibe Code Bench v1.1Building web apps from scratch | 42.17%±4.57 | 30.76%±5.28 |
Benchmarks
Legal Research Bench *
MiMo V2.5
0.00%± 2.00
(73/73)GLM 5.3 Flash
0.00%± 3.46
(73/73)Finance Agent (v2) *
MiMo V2.5
0.00%± 0.11
(74/74)GLM 5.3 Flash
0.00%± 2.06
(74/74)Tax Agent Bench *
MiMo V2.5
0.00%± 2.71
(65/65)GLM 5.3 Flash
0.00%± 3.26
(65/65)MedCode *
MiMo V2.5
0.00%± 2.02
(104/104)GLM 5.3 Flash
N/ATerminal-Bench Science
MiMo V2.5
N/AGLM 5.3 Flash
0.00%± 2.01
(38/38)Code Migration *
MiMo V2.5
0.00%± 3.69
(73/73)GLM 5.3 Flash
0.00%± 4.21
(73/73)Vibe Code Bench v1.1 *
MiMo V2.5
0.00%± 4.57
(108/108)GLM 5.3 Flash
0.00%± 5.28
(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
29.90%
vs.45.26%
Finance
50.41%
vs.62.83%
Healthcare
52.02%
vs.88.94%
Math
16.00%
vs.21.00%
Science
N/A
vs.2.86%
Academic
81.50%
vs.86.14%
Education
43.27%
vs.N/A
Coding
52.23%
vs.41.56%
Cyber
N/A
vs.67.86%
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
$0.14
vs.$0.075
Input Cache Read/ 1M Tokens
$0.003
vs.$0.015
Output Cost/ 1M Tokens
$0.28
vs.$0.25
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | Xiaomi | zAI |
| Latency | N/A | N/A |
| Cost (In/Out) | $0.14 / $0.28 | $0.075 / $0.25 |
| Context Window | 1M | 1M |
| Max Output Token | 128k | 128k |
| Input Modality |