Compare Models
Select models (max 5)
DeepSeek V4 Flash 0731Muse Spark 1.2
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | 47.96%±1.24 | 49.29%±1.10 |
| Legal Research BenchAgentic US legal research | 30.29%±3.19 | 43.75%±3.45 |
| Finance Agent (v2)Core financial analyst tasks | 49.52%±0.47 | 60.60%±0.28 |
| Tax Agent BenchAgentic US corporate tax research | 62.56%±3.14 | 56.86%±2.32 |
| MedCodeMedical billing code support | 41.41%±2.15 | 49.35%±2.19 |
| Terminal-Bench ScienceExpert-authored scientific research workflows | 4.29%±2.44 | N/A |
| Code MigrationRewriting programs in new languages | 38.63%±4.38 | 29.95%±4.02 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 18.69%±3.54 | 6.06%±1.51 |
| Vibe Code Bench v1.1Building web apps from scratch | 74.74%±3.44 | 79.10%±3.31 |
Benchmarks
Vals Index *
DeepSeek V4 Flash 0731
0.00%± 1.24
(43/43)Muse Spark 1.2
0.00%± 1.10
(43/43)Legal Research Bench *
DeepSeek V4 Flash 0731
0.00%± 3.19
(73/73)Muse Spark 1.2
0.00%± 3.45
(73/73)Finance Agent (v2) *
DeepSeek V4 Flash 0731
0.00%± 0.47
(74/74)Muse Spark 1.2
0.00%± 0.28
(74/74)Tax Agent Bench *
DeepSeek V4 Flash 0731
0.00%± 3.14
(65/65)Muse Spark 1.2
0.00%± 2.32
(65/65)MedCode *
DeepSeek V4 Flash 0731
0.00%± 2.15
(104/104)Muse Spark 1.2
0.00%± 2.19
(104/104)Terminal-Bench Science
DeepSeek V4 Flash 0731
0.00%± 2.44
(38/38)Muse Spark 1.2
N/ACode Migration *
DeepSeek V4 Flash 0731
0.00%± 4.38
(73/73)Muse Spark 1.2
0.00%± 4.02
(73/73)Terminal-Bench 4.0
DeepSeek V4 Flash 0731
0.00%± 3.54
(43/43)Muse Spark 1.2
0.00%± 1.51
(43/43)Vibe Code Bench v1.1 *
DeepSeek V4 Flash 0731
0.00%± 3.44
(108/108)Muse Spark 1.2
0.00%± 3.31
(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
38.78%
vs.51.48%
Finance
59.94%
vs.64.05%
Healthcare
60.89%
vs.69.70%
Math
56.00%
vs.43.00%
Science
34.37%
vs.64.81%
Academic
88.05%
vs.87.20%
Education
N/A
vs.47.66%
Coding
48.94%
vs.39.58%
Cyber
72.08%
vs.69.52%
Social Mobility
N/A
vs.68.47%
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
$0.848
$1.942
Cost / TestVals Index
$0.848
vs.$1.942
Input Cost/ 1M Tokens
$0.44
vs.$1.25
Input Cache Read/ 1M Tokens
$0.014
vs.$0.15
Output Cost/ 1M Tokens
$1.32
vs.$4.25
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | DeepSeek | Meta |
| Latency | 2585.58s | 1376.30s |
| Cost (In/Out) | $0.44 / $1.32 | $1.25 / $4.25 |
| Context Window | 1M | 1M |
| Max Output Token | 384k | 131k |
| Input Modality |