Compare Models
Select models (max 7)
DeepSeek V4 Flash 0731Muse Spark 1.2
| Legal Research BenchAgentic US legal research | 30.29%±3.19 | 43.75%±3.45 |
| Tax Agent BenchAgentic US corporate tax research | 28.07%±3.16 | 32.80%±2.75 |
| 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 |
| 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
Legal Research Bench *
DeepSeek V4 Flash 0731
0.00%± 3.19
(98/98)Muse Spark 1.2
0.00%± 3.45
(98/98)Tax Agent Bench *
DeepSeek V4 Flash 0731
0.00%± 3.16
(89/89)Muse Spark 1.2
0.00%± 2.75
(89/89)MedCode *
DeepSeek V4 Flash 0731
0.00%± 2.15
(107/107)Muse Spark 1.2
0.00%± 2.19
(107/107)Terminal-Bench-Science
DeepSeek V4 Flash 0731
0.00%± 2.44
(47/47)Muse Spark 1.2
N/ATerminal-Bench 4.0
DeepSeek V4 Flash 0731
0.00%± 3.54
(68/68)Muse Spark 1.2
0.00%± 1.51
(68/68)Vibe Code Bench v1.1 *
DeepSeek V4 Flash 0731
0.00%± 3.44
(132/132)Muse Spark 1.2
0.00%± 3.31
(132/132)Overall performance
Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, legal, and tax
Comparison by Industry
Model performance on different sections of the economy.
Legal
54.00%
vs.65.18%
Finance
49.38%
vs.59.53%
Healthcare
60.89%
vs.69.70%
Math
56.00%
vs.43.00%
Science
34.37%
vs.64.81%
Academic
88.05%
vs.87.20%
Coding
50.41%
vs.41.18%
Cyber
72.08%
vs.34.76%
Social Mobility
N/A
vs.72.10%
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
N/A
N/A
Cost / TestVals Index
N/A
vs.N/A
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 | ||
| Latency | N/A | N/A |
| Cost (In/Out) | $0.3 / $1.2 | $1.25 / $4.25 |
| Context Window | 1M | 1M |
| Max Output Token | 384k | 131k |
| Input Modality |