Compare Models
Select models (max 5)
GPT 5.4 NanoMiMo V2.5
 |  |  |
|---|---|---|
| Legal Research BenchAgentic US legal research | 6.25%±1.68 | 9.13%±2.00 |
| Finance Agent (v2)Core financial analyst tasks | 38.22%±1.19 | 36.73%±0.11 |
| Tax Agent BenchAgentic US corporate tax research | 26.58%±2.52 | 29.16%±2.71 |
| MedCodeMedical billing code support | 41.03%±2.26 | 31.89%±2.02 |
| Code MigrationRewriting programs in new languages | 14.47%±4.03 | 14.23%±3.69 |
| Vibe Code Bench v1.1Building web apps from scratch | 26.10%±5.08 | 42.17%±4.57 |
Benchmarks
Legal Research Bench *
GPT 5.4 Nano
0.00%± 1.68
(73/73)MiMo V2.5
0.00%± 2.00
(73/73)Finance Agent (v2) *
GPT 5.4 Nano
0.00%± 1.19
(74/74)MiMo V2.5
0.00%± 0.11
(74/74)Tax Agent Bench *
GPT 5.4 Nano
0.00%± 2.52
(65/65)MiMo V2.5
0.00%± 2.71
(65/65)MedCode *
GPT 5.4 Nano
0.00%± 2.26
(104/104)MiMo V2.5
0.00%± 2.02
(104/104)Code Migration *
GPT 5.4 Nano
0.00%± 4.03
(73/73)MiMo V2.5
0.00%± 3.69
(73/73)Vibe Code Bench v1.1 *
GPT 5.4 Nano
0.00%± 5.08
(108/108)MiMo V2.5
0.00%± 4.57
(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
28.06%
vs.29.90%
Finance
47.21%
vs.50.41%
Healthcare
59.06%
vs.52.02%
Math
N/A
vs.16.00%
Academic
76.09%
vs.81.50%
Education
38.08%
vs.43.27%
Coding
48.59%
vs.52.23%
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
$0.20
vs.$0.14
Input Cache Read/ 1M Tokens
$0.02
vs.$0.003
Output Cost/ 1M Tokens
$1.25
vs.$0.28
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | OpenAI | Xiaomi |
| Latency | N/A | N/A |
| Cost (In/Out) | $0.2 / $1.25 | $0.14 / $0.28 |
| Context Window | 400k | 1M |
| Max Output Token | 128k | 128k |
| Input Modality |