Compare Models
Select models (max 5)
DeepSeek V4 Pro 0813Hy4 Preview
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | 47.63%±1.12 | 49.94%±1.15 |
| Legal Research BenchAgentic US legal research | 40.87%±3.42 | 45.19%±3.46 |
| Finance Agent (v2)Core financial analyst tasks | 50.39%±0.25 | 55.06%±0.31 |
| Tax Agent BenchAgentic US corporate tax research | 58.66%±3.14 | 63.71%±3.26 |
| MedCodeMedical billing code support | 42.47%±2.16 | 43.25%±2.13 |
| Terminal-Bench ScienceExpert-authored scientific research workflows | 4.29%±2.44 | 1.43%±1.43 |
| Code MigrationRewriting programs in new languages | 41.54%±4.30 | 47.43%±4.27 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 14.14%±2.02 | 8.08%±1.34 |
| Vibe Code Bench v1.1Building web apps from scratch | 82.30%±3.15 | 77.48%±4.04 |
Benchmarks
Vals Index *
DeepSeek V4 Pro 0813
0.00%± 1.12
(43/43)Hy4 Preview
0.00%± 1.15
(43/43)Legal Research Bench *
DeepSeek V4 Pro 0813
0.00%± 3.42
(73/73)Hy4 Preview
0.00%± 3.46
(73/73)Finance Agent (v2) *
DeepSeek V4 Pro 0813
0.00%± 0.25
(74/74)Hy4 Preview
0.00%± 0.31
(74/74)Tax Agent Bench *
DeepSeek V4 Pro 0813
0.00%± 3.14
(65/65)Hy4 Preview
0.00%± 3.26
(65/65)MedCode *
DeepSeek V4 Pro 0813
0.00%± 2.16
(104/104)Hy4 Preview
0.00%± 2.13
(104/104)Terminal-Bench Science
DeepSeek V4 Pro 0813
0.00%± 2.44
(38/38)Hy4 Preview
0.00%± 1.43
(38/38)Code Migration *
DeepSeek V4 Pro 0813
0.00%± 4.30
(73/73)Hy4 Preview
0.00%± 4.27
(73/73)Terminal-Bench 4.0
DeepSeek V4 Pro 0813
0.00%± 2.02
(43/43)Hy4 Preview
0.00%± 1.34
(43/43)Vibe Code Bench v1.1 *
DeepSeek V4 Pro 0813
0.00%± 3.15
(108/108)Hy4 Preview
0.00%± 4.04
(108/108)Overall performance
Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, and law
•2026-10-02
Comparison by Industry
Model performance on different sections of the economy.
Legal
43.58%
vs.46.04%
Finance
58.73%
vs.58.95%
Healthcare
61.32%
vs.63.42%
Math
50.00%
vs.75.00%
Science
4.29%
vs.35.34%
Academic
89.70%
vs.N/A
Coding
49.43%
vs.38.47%
Cyber
72.86%
vs.33.82%
Social Mobility
N/A
vs.68.61%
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
$3.352
$1.439
Cost / TestVals Index
$3.352
vs.$1.439
Input Cost/ 1M Tokens
$1.32
vs.$0.834
Input Cache Read/ 1M Tokens
$0.044
vs.$0.042
Output Cost/ 1M Tokens
$3.96
vs.$2.501
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | DeepSeek | Openrouter |
| Latency | 3845.24s | 3656.53s |
| Cost (In/Out) | $1.32 / $3.96 | $0.834 / $2.501 |
| Context Window | 1M | 1M |
| Max Output Token | 384k | 64k |
| Input Modality |