Compare Models
Select models (max 7)
Hy4Mistral Large 4
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | 59.35%±1.08 | 56.53%±1.26 |
| Legal Research BenchAgentic US legal research | 41.35%±3.42 | 35.58%±3.33 |
| Finance Agent v2.1Core financial analyst tasks | 64.70%±2.05 | 61.72%±2.05 |
| Tax Agent BenchAgentic US corporate tax research | 34.40%±3.30 | 30.67%±3.30 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 39.39%±0.88 | 26.26%±5.13 |
| Vibe Code Bench v1.1Building web apps from scratch | 81.01%±3.55 | 81.56%±3.29 |
Benchmarks
Vals Index *
Hy4
0.00%± 1.08
(33/33)Mistral Large 4
0.00%± 1.26
(33/33)Legal Research Bench *
Hy4
0.00%± 3.42
(90/90)Mistral Large 4
0.00%± 3.33
(90/90)Finance Agent v2.1 *
Hy4
0.00%± 2.05
(36/36)Mistral Large 4
0.00%± 2.05
(36/36)Tax Agent Bench *
Hy4
0.00%± 3.30
(81/81)Mistral Large 4
0.00%± 3.30
(81/81)Terminal-Bench 4.0
Hy4
0.00%± 0.88
(60/60)Mistral Large 4
0.00%± 5.13
(60/60)Vibe Code Bench v1.1 *
Hy4
0.00%± 3.55
(124/124)Mistral Large 4
0.00%± 3.29
(124/124)Overall performance
Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, legal, and tax
•2026-11-04
Comparison by Industry
Model performance on different sections of the economy.
Legal
26.92%
vs.25.70%
Finance
55.09%
vs.53.69%
Coding
60.20%
vs.53.91%
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
$1.72
$3.717
Cost / TestVals Index
$1.72
vs.$3.717
Input Cost/ 1M Tokens
$0.834
vs.$0.70
Input Cache Read/ 1M Tokens
$0.042
vs.$0.07
Output Cost/ 1M Tokens
$2.501
vs.$2.10
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | Openrouter | Mistral AI |
| Latency | 3091.47s | 2868.04s |
| Cost (In/Out) | $0.834 / $2.501 | $0.7 / $2.1 |
| Context Window | 1M | 1M |
| Max Output Token | 66k | 256k |
| Input Modality |