Compare Models
Select models (max 7)
Gemini 3.7 FlashMuse Spark 1.3
 |  |  |
|---|---|---|
| Legal Research BenchAgentic US legal research | 34.62%±3.31 | 40.87%±3.42 |
| Tax Agent BenchAgentic US corporate tax research | 22.80%±3.03 | 35.97%±3.42 |
| MedCodeMedical billing code support | 53.39%±2.12 | N/A |
| Terminal-Bench-ScienceExpert-authored scientific research workflows | 7.14%±3.10 | 4.29%±2.44 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 12.12%±3.03 | 10.61%±1.75 |
| Vibe Code Bench v1.1Building web apps from scratch | 70.39%±4.84 | 82.86%±2.90 |
Benchmarks
Legal Research Bench *
Gemini 3.7 Flash
0.00% ± 3.31
(84/84)Muse Spark 1.3
0.00%± 3.42
(84/84)Tax Agent Bench *
Gemini 3.7 Flash
0.00%± 3.03
(75/75)Muse Spark 1.3
0.00%± 3.42
(75/75)MedCode *
Gemini 3.7 Flash
0.00%± 2.12
(107/107)Muse Spark 1.3
N/ATerminal-Bench-Science
Gemini 3.7 Flash
0.00%± 3.10
(42/42)Muse Spark 1.3
0.00%± 2.44
(42/42)Terminal-Bench 4.0
Gemini 3.7 Flash
0.00%± 3.03
(54/54)Muse Spark 1.3
0.00%± 1.75
(54/54)Vibe Code Bench v1.1 *
Gemini 3.7 Flash
0.00%± 4.84
(118/118)Muse Spark 1.3
0.00%± 2.90
(118/118)Overall performance
Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, and law
•2026-10-22
Comparison by Industry
Model performance on different sections of the economy.
Legal
60.94%
vs.40.87%
Finance
54.73%
vs.35.97%
Healthcare
68.67%
vs.N/A
Math
58.00%
vs.55.00%
Science
7.14%
vs.4.29%
Academic
91.01%
vs.N/A
Education
49.23%
vs.N/A
Coding
55.10%
vs.34.48%
Cyber
24.16%
vs.69.41%
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
$1.50
vs.$1.25
Input Cache Read/ 1M Tokens
$0.15
vs.$0.15
Output Cost/ 1M Tokens
$7.50
vs.$4.25
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | Google | Meta |
| Latency | N/A | N/A |
| Cost (In/Out) | $1.5 / $7.5 | $1.25 / $4.25 |
| Context Window | 1M | 1M |
| Max Output Token | 66k | 131k |
| Input Modality |