Compare Models

Select models (max 5)
Claude Sonnet 4 (Nonthinking)MiniMax-M3.1-Flash
Benchmarks

Vals Index *

Claude Sonnet 4 (Nonthinking)
N/A
MiniMax-M3.1-Flash
0.00%± 1.07
(22/22)

Legal Research Bench *

Claude Sonnet 4 (Nonthinking)
N/A
MiniMax-M3.1-Flash
0.00%± 3.30
(81/81)

Finance Agent v2.1 *

Claude Sonnet 4 (Nonthinking)
N/A
MiniMax-M3.1-Flash
0.00%± 2.07
(27/27)

Tax Agent Bench *

Claude Sonnet 4 (Nonthinking)
N/A
MiniMax-M3.1-Flash
0.00%± 3.34
(72/72)

MedCode *

Claude Sonnet 4 (Nonthinking)
0.00%± 1.91
(107/107)
MiniMax-M3.1-Flash
N/A

Terminal-Bench 4.0

Claude Sonnet 4 (Nonthinking)
N/A
MiniMax-M3.1-Flash
0.00%± 1.01
(51/51)

Vibe Code Bench v1.1 *

Claude Sonnet 4 (Nonthinking)
N/A
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

2026-10-19

Comparison by Industry

Model performance on different sections of the economy.

Legal
82.95%
20.82%
Finance
66.05%
52.94%
Healthcare
53.18%
N/A
Academic
73.75%
N/A
Education
35.00%
N/A
Coding
59.67%
49.60%

Cost Analysis

Per task and per token model pricing.

Vals Index · USD
N/A
$0.66
Cost / TestVals Index
N/A
$0.66
Input Cost/ 1M Tokens
$3.00
$0.15
Input Cache Write/ 1M Tokens
$3.75
N/A
Input Cache Read/ 1M Tokens
$0.30
$0.015
Output Cost/ 1M Tokens
$15.00
$0.60

Model Metadata

Basic information about each model.

Model provider
AnthropicAnthropic
MiniMaxMiniMax
LatencyN/A2597.84s
Cost (In/Out)$3 / $15$0.15 / $0.6
Context Window200k1M
Max Output Token64k524k
Input Modality