Compare Models
Select models (max 7)
Step 5 PreviewHy4 Preview
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | N/A | 53.21%±1.13 |
| Legal Research BenchAgentic US legal research | 40.38%±3.41 | 45.19%±3.46 |
| Finance Agent v2.1Core financial analyst tasks | 58.90%±2.05 | 61.62%±2.06 |
| Tax Agent BenchAgentic US corporate tax research | 27.27%±3.11 | 32.62%±3.38 |
| MedCodeMedical billing code support | N/A | 43.25%±2.13 |
| Terminal-Bench-ScienceExpert-authored scientific research workflows | 2.86%±2.01 | 1.43%±1.43 |
| Code Migration v1.1Rewriting programs in new languages | 47.00%±3.43 | 45.36%±3.59 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 31.82%±2.62 | 8.08%±1.34 |
| Vibe Code Bench v1.1Building web apps from scratch | 70.40%±4.27 | 77.48%±4.04 |
Benchmarks
Vals Index *
Step 5 Preview
N/AHy4 Preview
0.00%± 1.13
(26/26)Legal Research Bench *
Step 5 Preview
0.00%± 3.41
(84/84)Hy4 Preview
0.00%± 3.46
(84/84)Finance Agent v2.1 *
Step 5 Preview
0.00%± 2.05
(30/30)Hy4 Preview
0.00%± 2.06
(30/30)Tax Agent Bench *
Step 5 Preview
0.00%± 3.11
(75/75)Hy4 Preview
0.00%± 3.38
(75/75)MedCode *
Step 5 Preview
N/AHy4 Preview
0.00%± 2.13
(107/107)Terminal-Bench-Science
Step 5 Preview
0.00%± 2.01
(42/42)Hy4 Preview
0.00%± 1.43
(42/42)Code Migration v1.1 *
Step 5 Preview
0.00%± 3.43
(28/28)Hy4 Preview
0.00%± 3.59
(28/28)Terminal-Bench 4.0
Step 5 Preview
0.00%± 2.62
(54/54)Hy4 Preview
0.00%± 1.34
(54/54)Vibe Code Bench v1.1 *
Step 5 Preview
0.00%± 4.27
(118/118)Hy4 Preview
0.00%± 4.04
(118/118)Overall performance
Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, and law
•2026-10-22
Comparison by Industry
Model performance on different sections of the economy.
Legal
40.38%
vs.45.90%
Finance
51.91%
vs.54.40%
Healthcare
N/A
vs.63.42%
Math
42.00%
vs.75.00%
Science
29.58%
vs.35.34%
Coding
45.62%
vs.38.05%
Cyber
0.38%
vs.33.82%
Social Mobility
58.12%
vs.68.61%
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
N/A
$1.446
Cost / TestVals Index
N/A
vs.$1.446
Input Cost/ 1M Tokens
$1.00
vs.$0.834
Input Cache Read/ 1M Tokens
$0.05
vs.$0.042
Output Cost/ 1M Tokens
$2.70
vs.$2.501
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | Stepfun | Openrouter |
| Latency | N/A | 3562.64s |
| Cost (In/Out) | $1 / $2.7 | $0.834 / $2.501 |
| Context Window | 1M | 1M |
| Max Output Token | 1M | 64k |
| Input Modality |