Compare Models
Select models (max 5)
Claude Opus 4.7DeepSeek V4.1 Flash
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | N/A | 51.32%±1.13 |
| Legal Research BenchAgentic US legal research | 38.46%±3.38 | 41.35%±3.42 |
| Finance Agent (v2)Core financial analyst tasks | 51.51%±0.49 | 53.48%±0.39 |
| Tax Agent BenchAgentic US corporate tax research | 63.86%±3.14 | 62.46%±3.15 |
| MedCodeMedical billing code support | 54.86%±2.21 | 41.17%±2.04 |
| Terminal-Bench ScienceExpert-authored scientific research workflows | N/A | 0.00%±0.00 |
| Code MigrationRewriting programs in new languages | 43.88%±4.22 | 45.62%±4.29 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | N/A | 19.70%±1.75 |
| Vibe Code Bench v1.1Building web apps from scratch | 71.00%±4.51 | 84.74%±2.89 |
Benchmarks
Vals Index *
Claude Opus 4.7
N/ADeepSeek V4.1 Flash
0.00%± 1.13
(43/43)Legal Research Bench *
Claude Opus 4.7
0.00%± 3.38
(73/73)DeepSeek V4.1 Flash
0.00%± 3.42
(73/73)Finance Agent (v2) *
Claude Opus 4.7
0.00%± 0.49
(74/74)DeepSeek V4.1 Flash
0.00%± 0.39
(74/74)Tax Agent Bench *
Claude Opus 4.7
0.00%± 3.14
(65/65)DeepSeek V4.1 Flash
0.00%± 3.15
(65/65)MedCode *
Claude Opus 4.7
0.00%± 2.21
(104/104)DeepSeek V4.1 Flash
0.00%± 2.04
(104/104)Terminal-Bench Science
Claude Opus 4.7
N/ADeepSeek V4.1 Flash
0.00%± 0.00
(38/38)Code Migration *
Claude Opus 4.7
0.00%± 4.22
(73/73)DeepSeek V4.1 Flash
0.00%± 4.29
(73/73)Terminal-Bench 4.0
Claude Opus 4.7
N/ADeepSeek V4.1 Flash
0.00%± 1.75
(43/43)Vibe Code Bench v1.1 *
Claude Opus 4.7
0.00%± 4.51
(108/108)DeepSeek V4.1 Flash
0.00%± 2.89
(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
43.46%
vs.43.76%
Finance
64.93%
vs.57.72%
Healthcare
68.91%
vs.63.34%
Math
N/A
vs.54.00%
Science
N/A
vs.29.65%
Academic
88.52%
vs.N/A
Education
56.10%
vs.47.88%
Coding
56.39%
vs.39.57%
Cyber
N/A
vs.37.23%
Social Mobility
N/A
vs.64.28%
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
N/A
$0.332
Cost / TestVals Index
N/A
vs.$0.332
Input Cost/ 1M Tokens
$5.00
vs.$0.30
Input Cache Write/ 1M Tokens
$6.25
vs.N/A
Input Cache Read/ 1M Tokens
$0.50
vs.$0.006
Output Cost/ 1M Tokens
$25.00
vs.$1.20
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | Anthropic | DeepSeek |
| Latency | N/A | 1673.17s |
| Cost (In/Out) | $5 / $25 | $0.3 / $1.2 |
| Context Window | 1M | 1M |
| Max Output Token | 128k | 384k |
| Input Modality |