Compare Models
Select models (max 5)
DeepSeek V4.1 FlashMuse Spark 1.3
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | 51.32%±1.13 | 53.20%±1.07 |
| Legal Research BenchAgentic US legal research | 41.35%±3.42 | 40.87%±3.42 |
| Finance Agent (v2)Core financial analyst tasks | 53.48%±0.39 | 58.90%±0.44 |
| Tax Agent BenchAgentic US corporate tax research | 26.63%±3.14 | 35.97%±3.42 |
| MedCodeMedical billing code support | 41.17%±2.04 | N/A |
| Terminal-Bench-ScienceExpert-authored scientific research workflows | 0.00%±0.00 | 4.29%±2.44 |
| Code MigrationRewriting programs in new languages | 45.62%±4.29 | 27.58%±4.07 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 19.70%±1.75 | 10.61%±1.75 |
| Vibe Code Bench v1.1Building web apps from scratch | 84.74%±2.89 | 82.86%±2.90 |
Benchmarks
Vals Index *
DeepSeek V4.1 Flash
0.00%± 1.13
(50/50)Muse Spark 1.3
0.00%± 1.07
(50/50)Legal Research Bench *
DeepSeek V4.1 Flash
0.00%± 3.42
(80/80)Muse Spark 1.3
0.00%± 3.42
(80/80)Finance Agent (v2) *
DeepSeek V4.1 Flash
0.00%± 0.39
(80/80)Muse Spark 1.3
0.00%± 0.44
(80/80)Tax Agent Bench *
DeepSeek V4.1 Flash
0.00%± 3.14
(71/71)Muse Spark 1.3
0.00%± 3.42
(71/71)MedCode *
DeepSeek V4.1 Flash
0.00%± 2.04
(107/107)Muse Spark 1.3
N/ATerminal-Bench-Science
DeepSeek V4.1 Flash
0.00%± 0.00
(41/41)Muse Spark 1.3
0.00%± 2.44
(41/41)Code Migration *
DeepSeek V4.1 Flash
0.00%± 4.29
(79/79)Muse Spark 1.3
0.00%± 4.07
(79/79)Terminal-Bench 4.0
DeepSeek V4.1 Flash
0.00%± 1.75
(50/50)Muse Spark 1.3
0.00%± 1.75
(50/50)Vibe Code Bench v1.1 *
DeepSeek V4.1 Flash
0.00%± 2.89
(114/114)Muse Spark 1.3
0.00%± 2.90
(114/114)Overall performance
Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, and law
•2026-10-18
Comparison by Industry
Model performance on different sections of the economy.
Legal
43.76%
vs.31.89%
Finance
45.77%
vs.52.53%
Healthcare
63.34%
vs.N/A
Math
54.00%
vs.55.00%
Science
29.65%
vs.4.29%
Education
47.88%
vs.N/A
Coding
40.43%
vs.33.10%
Cyber
37.23%
vs.69.41%
Social Mobility
64.28%
vs.N/A
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
$0.332
$3.376
Cost / TestVals Index
$0.332
vs.$3.376
Input Cost/ 1M Tokens
$0.30
vs.$1.25
Input Cache Read/ 1M Tokens
$0.006
vs.$0.15
Output Cost/ 1M Tokens
$1.20
vs.$4.25
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | DeepSeek | Meta |
| Latency | 1673.17s | 1965.59s |
| Cost (In/Out) | $0.3 / $1.2 | $1.25 / $4.25 |
| Context Window | 1M | 1M |
| Max Output Token | 384k | 131k |
| Input Modality |