Compare Models
Select models (max 7)
MiniMax-M3Inkling
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | N/A | 28.96%±1.12 |
| Legal Research BenchAgentic US legal research | 29.81%±3.18 | 28.36%±3.13 |
| Finance Agent v2.1Core financial analyst tasks | 54.34%±2.02 | 49.87%±2.12 |
| Tax Agent BenchAgentic US corporate tax research | 20.59%±2.87 | 15.29%±2.42 |
| MedCodeMedical billing code support | 46.29%±2.10 | 41.19%±2.23 |
| Code Migration v1.1Rewriting programs in new languages | 20.90%±3.44 | 8.82%±2.71 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 1.01%±1.01 | 0.51%±0.51 |
| Vibe Code Bench v1.1Building web apps from scratch | 47.57%±5.44 | 19.21%±3.66 |
Benchmarks
Vals Index *
MiniMax-M3
N/AInkling
0.00%± 1.12
(26/26)Legal Research Bench *
MiniMax-M3
0.00%± 3.18
(84/84)Inkling
0.00%± 3.13
(84/84)Finance Agent v2.1 *
MiniMax-M3
0.00%± 2.02
(30/30)Inkling
0.00%± 2.12
(30/30)Tax Agent Bench *
MiniMax-M3
0.00%± 2.87
(75/75)Inkling
0.00%± 2.42
(75/75)MedCode *
MiniMax-M3
0.00%± 2.10
(107/107)Inkling
0.00%± 2.23
(107/107)Code Migration v1.1 *
MiniMax-M3
0.00%± 3.44
(28/28)Inkling
0.00%± 2.71
(28/28)Terminal-Bench 4.0
MiniMax-M3
0.00%± 1.01
(54/54)Inkling
0.00%± 0.51
(54/54)Vibe Code Bench v1.1 *
MiniMax-M3
0.00%± 5.44
(118/118)Inkling
0.00%± 3.66
(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
57.61%
vs.38.35%
Finance
55.15%
vs.49.09%
Healthcare
66.77%
vs.63.30%
Math
18.00%
vs.0.00%
Academic
86.02%
vs.83.97%
Education
50.57%
vs.36.55%
Coding
40.08%
vs.26.67%
Cyber
65.00%
vs.33.39%
Social Mobility
64.14%
vs.58.46%
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
N/A
$1.848
Cost / TestVals Index
N/A
vs.$1.848
Input Cost/ 1M Tokens
$0.60
vs.$1.00
Input Cache Read/ 1M Tokens
$0.12
vs.$0.17
Output Cost/ 1M Tokens
$2.40
vs.$4.05
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | MiniMax | Thinking Machines |
| Latency | N/A | 1032.92s |
| Cost (In/Out) | $0.6 / $2.4 | $1 / $4.05 |
| Context Window | 1M | 256k |
| Max Output Token | 512k | 256k |
| Input Modality |