Compare Models
Select models (max 7)
Mistral Medium 3.5Bison 1
| Legal Research BenchAgentic US legal research | 9.13%±2.00 | N/A |
| Tax Agent BenchAgentic US corporate tax research | 4.48%±1.47 | N/A |
| MedCodeMedical billing code support | 33.75%±1.15 | N/A |
| Vibe Code Bench v1.1Building web apps from scratch | 2.89%±1.71 | N/A |
Benchmarks
Legal Research Bench *
Mistral Medium 3.5
0.00%± 2.00
(100/100)Bison 1
N/ATax Agent Bench *
Mistral Medium 3.5
0.00%± 1.47
(91/91)Bison 1
N/AMedCode *
Mistral Medium 3.5
0.00%± 1.15
(109/109)Bison 1
N/AVibe Code Bench v1.1 *
Mistral Medium 3.5
0.00%± 1.71
(134/134)Bison 1
N/AOverall performance
Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, legal, and tax
No selected models have a Vals Index score.
Comparison by Industry
Model performance on different sections of the economy.
Legal
9.13%
vs.N/A
Finance
33.79%
vs.99.08%
Healthcare
50.74%
vs.N/A
Math
9.00%
vs.N/A
Academic
55.09%
vs.N/A
Education
71.97%
vs.N/A
Coding
34.64%
vs.N/A
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
$1.50
vs.$0.10
Input Cache Read/ 1M Tokens
$0.15
vs.N/A
Output Cost/ 1M Tokens
$7.50
vs.$0.00
Model Metadata
Basic information about each model.
| Model provider | ||
| Latency | N/A | N/A |
| Cost (In/Out) | $1.5 / $7.5 | $0.1 / $0 |
| Context Window | 262k | 131k |
| Max Output Token | 80k | 0 |
| Input Modality |