Compare Models
Select models (max 5)
DeepSeek V4.1 Flash 1017Muse Spark 1.3 Max
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | 56.58%±1.27 | 58.16%±1.19 |
| Legal Research BenchAgentic US legal research | 45.19%±3.46 | 55.29%±3.46 |
| Finance Agent (v2)Core financial analyst tasks | 56.96%±2.05 | 59.96%±2.06 |
| Tax Agent BenchAgentic US corporate tax research | 44.35%±3.57 | 42.44%±3.51 |
| Terminal-Bench-ScienceExpert-authored scientific research workflows | N/A | 10.00%±3.61 |
| Code MigrationRewriting programs in new languages | 44.21%±4.46 | 47.41%±4.26 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 31.82%±2.62 | 24.75%±0.51 |
| Vibe Code Bench v1.1Building web apps from scratch | 87.73%±2.75 | 85.86%±2.51 |
Benchmarks
Vals Index *
DeepSeek V4.1 Flash 1017
0.00%± 1.27
(50/50)Muse Spark 1.3 Max
0.00%± 1.19
(50/50)Legal Research Bench *
DeepSeek V4.1 Flash 1017
0.00%± 3.46
(80/80)Muse Spark 1.3 Max
0.00%± 3.46
(80/80)Finance Agent (v2) *
DeepSeek V4.1 Flash 1017
0.00%± 2.05
(80/80)Muse Spark 1.3 Max
0.00%± 2.06
(80/80)Tax Agent Bench *
DeepSeek V4.1 Flash 1017
0.00%± 3.57
(71/71)Muse Spark 1.3 Max
0.00%± 3.51
(71/71)Terminal-Bench-Science
DeepSeek V4.1 Flash 1017
N/AMuse Spark 1.3 Max
0.00%± 3.61
(41/41)Code Migration *
DeepSeek V4.1 Flash 1017
0.00%± 4.46
(79/79)Muse Spark 1.3 Max
0.00%± 4.26
(79/79)Terminal-Bench 4.0
DeepSeek V4.1 Flash 1017
0.00%± 2.62
(50/50)Muse Spark 1.3 Max
0.00%± 0.51
(50/50)Vibe Code Bench v1.1 *
DeepSeek V4.1 Flash 1017
0.00%± 2.75
(114/114)Muse Spark 1.3 Max
0.00%± 2.51
(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
27.18%
vs.39.52%
Finance
54.37%
vs.56.61%
Math
N/A
vs.58.00%
Science
N/A
vs.23.02%
Coding
54.59%
vs.40.09%
Cyber
N/A
vs.38.28%
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
$0.637
$3.787
Cost / TestVals Index
$0.637
vs.$3.787
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 | 2193.12s | 1414.24s |
| Cost (In/Out) | $0.3 / $1.2 | $1.25 / $4.25 |
| Context Window | 1M | 1M |
| Max Output Token | 384k | 131k |
| Input Modality |