Compare Models
Select models (max 5)
Muse Spark 1.3 MaxGPT-5.6 Sol
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | 58.16%±1.19 | 58.01%±1.02 |
| Legal Research BenchAgentic US legal research | 55.29%±3.46 | 48.08%±3.47 |
| Finance Agent (v2)Core financial analyst tasks | 59.96%±2.06 | 53.76%±0.85 |
| Tax Agent BenchAgentic US corporate tax research | 72.44%±2.88 | 67.95%±3.12 |
| MedCodeMedical billing code support | N/A | 43.97%±2.26 |
| Terminal-Bench ScienceExpert-authored scientific research workflows | 10.00%±3.61 | 20.00%±4.82 |
| Code MigrationRewriting programs in new languages | 47.41%±4.26 | 52.92%±4.35 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 24.75%±0.51 | 37.88%±0.00 |
| Vibe Code Bench v1.1Building web apps from scratch | 85.86%±2.51 | 80.50%±3.72 |
Benchmarks
Vals Index *
Muse Spark 1.3 Max
0.00%± 1.19
(43/43)GPT-5.6 Sol
0.00%± 1.02
(43/43)Legal Research Bench *
Muse Spark 1.3 Max
0.00%± 3.46
(73/73)GPT-5.6 Sol
0.00%± 3.47
(73/73)Finance Agent (v2) *
Muse Spark 1.3 Max
0.00%± 2.06
(74/74)GPT-5.6 Sol
0.00%± 0.85
(74/74)Tax Agent Bench *
Muse Spark 1.3 Max
0.00%± 2.88
(65/65)GPT-5.6 Sol
0.00%± 3.12
(65/65)MedCode *
Muse Spark 1.3 Max
N/AGPT-5.6 Sol
0.00%± 2.26
(104/104)Terminal-Bench Science
Muse Spark 1.3 Max
0.00%± 3.61
(38/38)GPT-5.6 Sol
0.00%± 4.82
(38/38)Code Migration *
Muse Spark 1.3 Max
0.00%± 4.26
(73/73)GPT-5.6 Sol
0.00%± 4.35
(73/73)Terminal-Bench 4.0
Muse Spark 1.3 Max
0.00%± 0.51
(43/43)GPT-5.6 Sol
0.00%± 0.00
(43/43)Vibe Code Bench v1.1 *
Muse Spark 1.3 Max
0.00%± 2.51
(108/108)GPT-5.6 Sol
0.00%± 3.72
(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
39.52%
vs.45.85%
Finance
66.61%
vs.67.22%
Healthcare
N/A
vs.64.60%
Math
58.00%
vs.83.00%
Science
23.02%
vs.41.48%
Academic
N/A
vs.91.05%
Education
N/A
vs.52.56%
Coding
39.59%
vs.57.43%
Cyber
72.74%
vs.53.42%
Social Mobility
N/A
vs.66.51%
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
$3.787
$14.24
Cost / TestVals Index
$3.787
vs.$14.24
Input Cost/ 1M Tokens
$1.25
vs.$4.00
Input Cache Write/ 1M Tokens
N/A
vs.$5.00
Input Cache Read/ 1M Tokens
$0.15
vs.$0.40
Output Cost/ 1M Tokens
$4.25
vs.$20.00
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | Meta | OpenAI |
| Latency | 1413.29s | 2242.72s |
| Cost (In/Out) | $1.25 / $4.25 | $4 / $20 |
| Context Window | 1M | 1M |
| Max Output Token | 131k | 128k |
| Input Modality |