Compare Models
Select models (max 5)
DeepSeek V4.1 FlashGPT-5.6 Terra
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | 51.32%±1.13 | 53.09%±1.29 |
| Legal Research BenchAgentic US legal research | 41.35%±3.42 | 41.35%±3.42 |
| Finance Agent (v2)Core financial analyst tasks | 53.48%±0.39 | 54.44%±2.07 |
| Tax Agent BenchAgentic US corporate tax research | 62.46%±3.15 | 65.20%±3.19 |
| MedCodeMedical billing code support | 41.17%±2.04 | 43.41%±2.17 |
| Terminal-Bench ScienceExpert-authored scientific research workflows | 0.00%±0.00 | 10.00%±3.61 |
| Code MigrationRewriting programs in new languages | 45.62%±4.29 | 47.80%±4.28 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 19.70%±1.75 | 22.73%±2.31 |
| Vibe Code Bench v1.1Building web apps from scratch | 84.74%±2.89 | 74.59%±4.20 |
Benchmarks
Vals Index *
DeepSeek V4.1 Flash
0.00%± 1.13
(43/43)GPT-5.6 Terra
0.00%± 1.29
(43/43)Legal Research Bench *
DeepSeek V4.1 Flash
0.00%± 3.42
(73/73)GPT-5.6 Terra
0.00%± 3.42
(73/73)Finance Agent (v2) *
DeepSeek V4.1 Flash
0.00%± 0.39
(74/74)GPT-5.6 Terra
0.00%± 2.07
(74/74)Tax Agent Bench *
DeepSeek V4.1 Flash
0.00%± 3.15
(65/65)GPT-5.6 Terra
0.00%± 3.19
(65/65)MedCode *
DeepSeek V4.1 Flash
0.00%± 2.04
(104/104)GPT-5.6 Terra
0.00%± 2.17
(104/104)Terminal-Bench Science
DeepSeek V4.1 Flash
0.00%± 0.00
(38/38)GPT-5.6 Terra
0.00%± 3.61
(38/38)Code Migration *
DeepSeek V4.1 Flash
0.00%± 4.29
(73/73)GPT-5.6 Terra
0.00%± 4.28
(73/73)Terminal-Bench 4.0
DeepSeek V4.1 Flash
0.00%± 1.75
(43/43)GPT-5.6 Terra
0.00%± 2.31
(43/43)Vibe Code Bench v1.1 *
DeepSeek V4.1 Flash
0.00%± 2.89
(108/108)GPT-5.6 Terra
0.00%± 4.20
(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
43.76%
vs.42.43%
Finance
57.72%
vs.65.87%
Healthcare
63.34%
vs.63.14%
Math
54.00%
vs.74.00%
Science
29.65%
vs.10.00%
Academic
N/A
vs.88.01%
Education
47.88%
vs.47.00%
Coding
39.57%
vs.54.25%
Cyber
37.23%
vs.72.08%
Social Mobility
64.28%
vs.62.38%
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
$0.332
$5.776
Cost / TestVals Index
$0.332
vs.$5.776
Input Cost/ 1M Tokens
$0.30
vs.$2.00
Input Cache Write/ 1M Tokens
N/A
vs.$2.50
Input Cache Read/ 1M Tokens
$0.006
vs.$0.20
Output Cost/ 1M Tokens
$1.20
vs.$12.00
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | DeepSeek | OpenAI |
| Latency | 1673.17s | 2138.85s |
| Cost (In/Out) | $0.3 / $1.2 | $2 / $12 |
| Context Window | 1M | 1M |
| Max Output Token | 384k | 128k |
| Input Modality |