Compare Models
Select models (max 5)
DeepSeek V4 Pro 0813Gemini 3.5 Flash
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | 47.63%±1.12 | 44.79%±1.10 |
| Legal Research BenchAgentic US legal research | 40.87%±3.42 | 30.77%±3.21 |
| Finance Agent (v2)Core financial analyst tasks | 50.39%±0.25 | 57.86%±0.23 |
| Tax Agent BenchAgentic US corporate tax research | 58.66%±3.14 | 53.53%±3.30 |
| MedCodeMedical billing code support | 42.47%±2.16 | 55.83%±2.11 |
| Terminal-Bench ScienceExpert-authored scientific research workflows | 4.29%±2.44 | 5.71%±2.79 |
| Code MigrationRewriting programs in new languages | 41.54%±4.30 | 26.75%±4.10 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 14.14%±2.02 | 6.06%±1.51 |
| Vibe Code Bench v1.1Building web apps from scratch | 82.30%±3.15 | 48.68%±4.73 |
Benchmarks
Vals Index *
DeepSeek V4 Pro 0813
0.00%± 1.12
(43/43)Gemini 3.5 Flash
0.00%± 1.10
(43/43)Legal Research Bench *
DeepSeek V4 Pro 0813
0.00%± 3.42
(73/73)Gemini 3.5 Flash
0.00%± 3.21
(73/73)Finance Agent (v2) *
DeepSeek V4 Pro 0813
0.00%± 0.25
(74/74)Gemini 3.5 Flash
0.00%± 0.23
(74/74)Tax Agent Bench *
DeepSeek V4 Pro 0813
0.00%± 3.14
(65/65)Gemini 3.5 Flash
0.00%± 3.30
(65/65)MedCode *
DeepSeek V4 Pro 0813
0.00%± 2.16
(104/104)Gemini 3.5 Flash
0.00%± 2.11
(104/104)Terminal-Bench Science
DeepSeek V4 Pro 0813
0.00%± 2.44
(38/38)Gemini 3.5 Flash
0.00%± 2.79
(38/38)Code Migration *
DeepSeek V4 Pro 0813
0.00%± 4.30
(73/73)Gemini 3.5 Flash
0.00%± 4.10
(73/73)Terminal-Bench 4.0
DeepSeek V4 Pro 0813
0.00%± 2.02
(43/43)Gemini 3.5 Flash
0.00%± 1.51
(43/43)Vibe Code Bench v1.1 *
DeepSeek V4 Pro 0813
0.00%± 3.15
(108/108)Gemini 3.5 Flash
0.00%± 4.73
(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.38.96%
Finance
58.73%
vs.63.48%
Healthcare
61.32%
vs.66.20%
Math
50.00%
vs.31.00%
Science
4.29%
vs.5.71%
Academic
89.70%
vs.90.15%
Education
N/A
vs.49.88%
Coding
49.43%
vs.42.95%
Cyber
72.86%
vs.N/A
Social Mobility
N/A
vs.59.47%
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
$3.352
$3.297
Cost / TestVals Index
$3.352
vs.$3.297
Input Cost/ 1M Tokens
$1.32
vs.$1.50
Input Cache Read/ 1M Tokens
$0.044
vs.$0.15
Output Cost/ 1M Tokens
$3.96
vs.$9.00
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | DeepSeek | Google |
| Latency | 3845.24s | 1097.11s |
| Cost (In/Out) | $1.32 / $3.96 | $1.5 / $9 |
| Context Window | 1M | 1M |
| Max Output Token | 384k | 66k |
| Input Modality |