Compare Models
Select models (max 5)
DeepSeek V4.1 FlashGPT 5.5
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | 51.32%±1.13 | N/A |
| Legal Research BenchAgentic US legal research | 41.35%±3.42 | 40.38%±3.41 |
| Finance Agent (v2)Core financial analyst tasks | 53.48%±0.39 | 51.76%±0.55 |
| Tax Agent BenchAgentic US corporate tax research | 62.46%±3.15 | 60.46%±3.22 |
| MedCodeMedical billing code support | 41.17%±2.04 | 49.10%±2.19 |
| Terminal-Bench ScienceExpert-authored scientific research workflows | 0.00%±0.00 | N/A |
| Code MigrationRewriting programs in new languages | 45.62%±4.29 | 45.16%±4.16 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 19.70%±1.75 | N/A |
| Vibe Code Bench v1.1Building web apps from scratch | 84.74%±2.89 | 69.85%±4.54 |
Benchmarks
Vals Index *
DeepSeek V4.1 Flash
0.00%± 1.13
(43/43)GPT 5.5
N/ALegal Research Bench *
DeepSeek V4.1 Flash
0.00%± 3.42
(73/73)GPT 5.5
0.00%± 3.41
(73/73)Finance Agent (v2) *
DeepSeek V4.1 Flash
0.00%± 0.39
(74/74)GPT 5.5
0.00%± 0.55
(74/74)Tax Agent Bench *
DeepSeek V4.1 Flash
0.00%± 3.15
(65/65)GPT 5.5
0.00%± 3.22
(65/65)MedCode *
DeepSeek V4.1 Flash
0.00%± 2.04
(104/104)GPT 5.5
0.00%± 2.19
(104/104)Terminal-Bench Science
DeepSeek V4.1 Flash
0.00%± 0.00
(38/38)GPT 5.5
N/ACode Migration *
DeepSeek V4.1 Flash
0.00%± 4.29
(73/73)GPT 5.5
0.00%± 4.16
(73/73)Terminal-Bench 4.0
DeepSeek V4.1 Flash
0.00%± 1.75
(43/43)GPT 5.5
N/AVibe Code Bench v1.1 *
DeepSeek V4.1 Flash
0.00%± 2.89
(108/108)GPT 5.5
0.00%± 4.54
(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.43.55%
Finance
57.72%
vs.64.10%
Healthcare
63.34%
vs.67.98%
Math
54.00%
vs.N/A
Science
29.65%
vs.N/A
Academic
N/A
vs.89.86%
Education
47.88%
vs.51.53%
Coding
39.57%
vs.57.60%
Cyber
37.23%
vs.3.82%
Social Mobility
64.28%
vs.60.89%
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
$0.332
N/A
Cost / TestVals Index
$0.332
vs.N/A
Input Cost/ 1M Tokens
$0.30
vs.$5.00
Input Cache Read/ 1M Tokens
$0.006
vs.$0.50
Output Cost/ 1M Tokens
$1.20
vs.$30.00
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | DeepSeek | OpenAI |
| Latency | 1673.17s | N/A |
| Cost (In/Out) | $0.3 / $1.2 | $5 / $30 |
| Context Window | 1M | 1M |
| Max Output Token | 384k | 128k |
| Input Modality |