Compare Models
Select models (max 7)
Gemini 3.1 Pro Preview (02/26)MiniMax-M3
| Legal Research BenchAgentic US legal research | 20.67%±2.81 | 29.81%±3.18 |
| Finance Agent v2.1Core financial analyst tasks | N/A | 54.34%±2.02 |
| Tax Agent BenchAgentic US corporate tax research | 9.29%±2.09 | 20.59%±2.87 |
| MedCodeMedical billing code support | 59.06%±2.00 | 46.29%±2.10 |
| Terminal-Bench-ScienceExpert-authored scientific research workflows | 1.43%±1.43 | N/A |
| Code Migration v1.1Rewriting programs in new languages | N/A | 20.90%±3.44 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 2.52%±0.51 | 1.01%±1.01 |
| Vibe Code Bench v1.1Building web apps from scratch | 32.03%±4.34 | 47.57%±5.44 |
Benchmarks
Legal Research Bench *
Gemini 3.1 Pro Preview (02/26)
0.00%± 2.81
(98/98)MiniMax-M3
0.00%± 3.18
(98/98)Finance Agent v2.1 *
Gemini 3.1 Pro Preview (02/26)
N/AMiniMax-M3
0.00%± 2.02
(44/44)Tax Agent Bench *
Gemini 3.1 Pro Preview (02/26)
0.00%± 2.09
(89/89)MiniMax-M3
0.00%± 2.87
(89/89)MedCode *
Gemini 3.1 Pro Preview (02/26)
0.00%± 2.00
(107/107)MiniMax-M3
0.00%± 2.10
(107/107)Terminal-Bench-Science
Gemini 3.1 Pro Preview (02/26)
0.00%± 1.43
(47/47)MiniMax-M3
N/ACode Migration v1.1 *
Gemini 3.1 Pro Preview (02/26)
N/AMiniMax-M3
0.00%± 3.44
(30/30)Terminal-Bench 4.0
Gemini 3.1 Pro Preview (02/26)
0.00%± 0.51
(68/68)MiniMax-M3
0.00%± 1.01
(68/68)Vibe Code Bench v1.1 *
Gemini 3.1 Pro Preview (02/26)
0.00%± 4.34
(132/132)MiniMax-M3
0.00%± 5.44
(132/132)Overall performance
Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, legal, and tax
Comparison by Industry
Model performance on different sections of the economy.
Legal
54.04%
vs.57.58%
Finance
50.52%
vs.55.15%
Healthcare
67.59%
vs.66.77%
Math
26.00%
vs.18.00%
Science
27.38%
vs.N/A
Academic
91.55%
vs.86.02%
Education
83.18%
vs.85.53%
Coding
42.28%
vs.44.49%
Cyber
0.00%
vs.65.00%
Social Mobility
60.26%
vs.67.65%
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
$2.00
vs.$0.30
Input Cache Read/ 1M Tokens
$0.20
vs.$0.06
Output Cost/ 1M Tokens
$12.00
vs.$1.20
Model Metadata
Basic information about each model.
| Model provider | ||
| Latency | N/A | N/A |
| Cost (In/Out) | $2 / $12 | $0.3 / $1.2 |
| Context Window | 1M | 1M |
| Max Output Token | 66k | 512k |
| Input Modality |