Compare Models
Select models (max 5)
DeepSeek V4GPT 5.4 Mini
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | 38.63%±1.16 | 33.17%±1.28 |
| Legal Research BenchAgentic US legal research | 23.08%±2.93 | 12.50%±2.30 |
| Finance Agent (v2)Core financial analyst tasks | 44.08%±0.65 | 45.36%±0.45 |
| Tax Agent BenchAgentic US corporate tax research | 58.50%±3.13 | 36.59%±3.10 |
| MedCodeMedical billing code support | 40.45%±2.12 | N/A |
| Code MigrationRewriting programs in new languages | 26.20%±4.04 | 12.94%±3.64 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 11.11%±1.34 | 2.52%±1.01 |
| Vibe Code Bench v1.1Building web apps from scratch | 49.93%±4.77 | 47.97%±5.61 |
Benchmarks
Vals Index *
DeepSeek V4
0.00%± 1.16
(43/43)GPT 5.4 Mini
0.00%± 1.28
(43/43)Legal Research Bench *
DeepSeek V4
0.00%± 2.93
(73/73)GPT 5.4 Mini
0.00%± 2.30
(73/73)Finance Agent (v2) *
DeepSeek V4
0.00%± 0.65
(74/74)GPT 5.4 Mini
0.00%± 0.45
(74/74)Tax Agent Bench *
DeepSeek V4
0.00%± 3.13
(65/65)GPT 5.4 Mini
0.00%± 3.10
(65/65)MedCode *
DeepSeek V4
0.00%± 2.12
(104/104)GPT 5.4 Mini
N/ACode Migration *
DeepSeek V4
0.00%± 4.04
(73/73)GPT 5.4 Mini
0.00%± 3.64
(73/73)Terminal-Bench 4.0
DeepSeek V4
0.00%± 1.34
(43/43)GPT 5.4 Mini
0.00%± 1.01
(43/43)Vibe Code Bench v1.1 *
DeepSeek V4
0.00%± 4.77
(108/108)GPT 5.4 Mini
0.00%± 5.61
(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
35.72%
vs.6.25%
Finance
56.57%
vs.52.42%
Healthcare
57.80%
vs.N/A
Math
16.00%
vs.N/A
Academic
88.32%
vs.82.29%
Education
N/A
vs.50.81%
Coding
43.34%
vs.36.32%
Social Mobility
62.92%
vs.N/A
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
$1.306
$1.452
Cost / TestVals Index
$1.306
vs.$1.452
Input Cost/ 1M Tokens
$1.32
vs.$0.75
Input Cache Read/ 1M Tokens
$0.044
vs.$0.075
Output Cost/ 1M Tokens
$3.96
vs.$4.50
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | DeepSeek | OpenAI |
| Latency | 1928.91s | 1788.54s |
| Cost (In/Out) | $1.32 / $3.96 | $0.75 / $4.5 |
| Context Window | 1M | 400k |
| Max Output Token | 384k | 128k |
| Input Modality |