Compare Models
Select models (max 5)
MiniMax-M3.1-FlashDeepSeek V4.1 Flash 1017
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | 53.78%±1.07 | 61.26%±1.05 |
| Legal Research BenchAgentic US legal research | 34.13%±3.30 | 45.19%±3.46 |
| Finance Agent v2.1Core financial analyst tasks | 58.83%±2.07 | 62.93%±2.03 |
| Tax Agent BenchAgentic US corporate tax research | 32.14%±3.34 | 44.35%±3.57 |
| Code Migration v1.1Rewriting programs in new languages | N/A | 67.52%±2.76 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 25.25%±1.01 | 31.82%±2.62 |
| Vibe Code Bench v1.1Building web apps from scratch | 73.94%±4.25 | 87.73%±2.75 |
Benchmarks
Vals Index *
MiniMax-M3.1-Flash
0.00%± 1.07
(22/22)DeepSeek V4.1 Flash 1017
0.00%± 1.05
(22/22)Legal Research Bench *
MiniMax-M3.1-Flash
0.00%± 3.30
(81/81)DeepSeek V4.1 Flash 1017
0.00%± 3.46
(81/81)Finance Agent v2.1 *
MiniMax-M3.1-Flash
0.00%± 2.07
(27/27)DeepSeek V4.1 Flash 1017
0.00%± 2.03
(27/27)Tax Agent Bench *
MiniMax-M3.1-Flash
0.00%± 3.34
(72/72)DeepSeek V4.1 Flash 1017
0.00%± 3.57
(72/72)Code Migration v1.1 *
MiniMax-M3.1-Flash
N/ADeepSeek V4.1 Flash 1017
0.00%± 2.76
(25/25)Terminal-Bench 4.0
MiniMax-M3.1-Flash
0.00%± 1.01
(51/51)DeepSeek V4.1 Flash 1017
0.00%± 2.62
(51/51)Vibe Code Bench v1.1 *
MiniMax-M3.1-Flash
0.00%± 4.25
(115/115)DeepSeek V4.1 Flash 1017
0.00%± 2.75
(115/115)Overall performance
Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, and law
•2026-10-19
Comparison by Industry
Model performance on different sections of the economy.
Legal
20.82%
vs.29.68%
Finance
52.94%
vs.58.82%
Coding
49.60%
vs.62.36%
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
$3.866
$0.657
Cost / TestVals Index
$3.866
vs.$0.657
Input Cost/ 1M Tokens
$0.60
vs.$0.30
Input Cache Read/ 1M Tokens
$0.12
vs.$0.006
Output Cost/ 1M Tokens
$2.40
vs.$1.20
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | MiniMax | DeepSeek |
| Latency | 2597.84s | 2394.71s |
| Cost (In/Out) | $0.6 / $2.4 | $0.3 / $1.2 |
| Context Window | 1M | 1M |
| Max Output Token | 524k | 384k |
| Input Modality |