Compare Models
Select models (max 5)
Claude Opus 4.6 (Nonthinking)MiniMax-M3.1-Flash
| Vals IndexGDP-weighted benchmark | N/A | 53.78%±1.07 |
| Legal Research BenchAgentic US legal research | N/A | 34.13%±3.30 |
| Finance Agent v2.1Core financial analyst tasks | N/A | 58.83%±2.07 |
| Tax Agent BenchAgentic US corporate tax research | N/A | 32.14%±3.34 |
| MedCodeMedical billing code support | 48.24%±2.05 | N/A |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | N/A | 25.25%±1.01 |
| Vibe Code Bench v1.1Building web apps from scratch | 57.57%±4.37 | 73.94%±4.25 |
Benchmarks
Vals Index *
Claude Opus 4.6 (Nonthinking)
N/AMiniMax-M3.1-Flash
0.00%± 1.07
(22/22)Legal Research Bench *
Claude Opus 4.6 (Nonthinking)
N/AMiniMax-M3.1-Flash
0.00%± 3.30
(81/81)Finance Agent v2.1 *
Claude Opus 4.6 (Nonthinking)
N/AMiniMax-M3.1-Flash
0.00%± 2.07
(27/27)Tax Agent Bench *
Claude Opus 4.6 (Nonthinking)
N/AMiniMax-M3.1-Flash
0.00%± 3.34
(72/72)MedCode *
Claude Opus 4.6 (Nonthinking)
0.00%± 2.05
(107/107)MiniMax-M3.1-Flash
N/ATerminal-Bench 4.0
Claude Opus 4.6 (Nonthinking)
N/AMiniMax-M3.1-Flash
0.00%± 1.01
(51/51)Vibe Code Bench v1.1 *
Claude Opus 4.6 (Nonthinking)
0.00%± 4.37
(115/115)MiniMax-M3.1-Flash
0.00%± 4.25
(115/115)Overall performance
Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, and law
Comparison by Industry
Model performance on different sections of the economy.
Legal
N/A
vs.20.82%
Finance
N/A
vs.52.94%
Healthcare
67.49%
vs.N/A
Coding
57.57%
vs.49.60%
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
N/A
$0.66
Cost / TestVals Index
N/A
vs.$0.66
Input Cost/ 1M Tokens
$5.00
vs.$0.15
Input Cache Write/ 1M Tokens
$6.25
vs.N/A
Input Cache Read/ 1M Tokens
$0.50
vs.$0.015
Output Cost/ 1M Tokens
$25.00
vs.$0.60
Model Metadata
Basic information about each model.
| Model provider | ||
| Latency | N/A | 2597.84s |
| Cost (In/Out) | $5 / $25 | $0.15 / $0.6 |
| Context Window | 1M | 1M |
| Max Output Token | 128k | 524k |
| Input Modality |