Compare Models
Select models (max 5)
Claude Sonnet 5DeepSeek V4.1 Flash
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | 51.77%±1.09 | 51.32%±1.13 |
| Legal Research BenchAgentic US legal research | 41.83%±3.43 | 41.35%±3.42 |
| Finance Agent (v2)Core financial analyst tasks | 53.91%±0.52 | 53.48%±0.39 |
| Tax Agent BenchAgentic US corporate tax research | 62.27%±3.19 | 62.46%±3.15 |
| MedCodeMedical billing code support | 47.54%±2.27 | 41.17%±2.04 |
| Terminal-Bench ScienceExpert-authored scientific research workflows | 2.86%±2.01 | 0.00%±0.00 |
| Code MigrationRewriting programs in new languages | 44.39%±4.25 | 45.62%±4.29 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 9.60%±1.01 | 19.70%±1.75 |
| Vibe Code Bench v1.1Building web apps from scratch | 81.33%±3.05 | 84.74%±2.89 |
Benchmarks
Vals Index *
Claude Sonnet 5
0.00%± 1.09
(30/30)DeepSeek V4.1 Flash
0.00%± 1.13
(30/30)Legal Research Bench *
Claude Sonnet 5
0.00%± 3.43
(71/71)DeepSeek V4.1 Flash
0.00%± 3.42
(71/71)Finance Agent (v2) *
Claude Sonnet 5
0.00%± 0.52
(72/72)DeepSeek V4.1 Flash
0.00%± 0.39
(72/72)Tax Agent Bench *
Claude Sonnet 5
0.00%± 3.19
(63/63)DeepSeek V4.1 Flash
0.00%± 3.15
(63/63)MedCode *
Claude Sonnet 5
0.00%± 2.27
(103/103)DeepSeek V4.1 Flash
0.00%± 2.04
(103/103)Terminal-Bench Science
Claude Sonnet 5
0.00%± 2.01
(33/33)DeepSeek V4.1 Flash
0.00%± 0.00
(33/33)Code Migration *
Claude Sonnet 5
0.00%± 4.25
(70/70)DeepSeek V4.1 Flash
0.00%± 4.29
(70/70)Terminal-Bench 4.0
Claude Sonnet 5
0.00%± 1.01
(31/31)DeepSeek V4.1 Flash
0.00%± 1.75
(31/31)Vibe Code Bench v1.1 *
Claude Sonnet 5
0.00%± 3.05
(105/105)DeepSeek V4.1 Flash
0.00%± 2.89
(105/105)Overall performance
Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, and law
•2026-09-29
Comparison by Industry
Model performance on different sections of the economy.
Legal
43.58%
vs.43.76%
Finance
65.63%
vs.57.72%
Healthcare
61.80%
vs.63.34%
Math
77.00%
vs.54.00%
Science
2.86%
vs.29.65%
Academic
86.48%
vs.N/A
Education
48.92%
vs.47.88%
Coding
44.74%
vs.46.09%
Beta
61.91%
vs.37.23%
Social Mobility
66.03%
vs.64.28%
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
$13.72
$0.332
Cost / TestVals Index
$13.72
vs.$0.332
Input Cost/ 1M Tokens
$2.00
vs.$0.30
Input Cache Write/ 1M Tokens
$2.50
vs.N/A
Input Cache Read/ 1M Tokens
$0.20
vs.$0.006
Output Cost/ 1M Tokens
$10.00
vs.$1.20
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | Anthropic | DeepSeek |
| Latency | 3255.62s | 1673.17s |
| Cost (In/Out) | $2 / $10 | $0.3 / $1.2 |
| Context Window | 1M | 1M |
| Max Output Token | 128k | 384k |
| Input Modality |