Compare Models
Select models (max 7)
Claude Sonnet 5Gemini 3.7 Flash
 |  |  |
|---|---|---|
| Legal Research BenchAgentic US legal research | 41.83%±3.43 | 34.62%±3.31 |
| Tax Agent BenchAgentic US corporate tax research | 29.37%±3.25 | 22.80%±3.03 |
| MedCodeMedical billing code support | 47.54%±2.27 | 53.39%±2.12 |
| Terminal-Bench-ScienceExpert-authored scientific research workflows | 5.71%±2.79 | 7.14%±3.10 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 10.61%±1.51 | 12.12%±3.03 |
| Vibe Code Bench v1.1Building web apps from scratch | 81.33%±3.05 | 70.39%±4.84 |
Benchmarks
Legal Research Bench *
Claude Sonnet 5
0.00%± 3.43
(94/94)Gemini 3.7 Flash
0.00%± 3.31
(94/94)Tax Agent Bench *
Claude Sonnet 5
0.00%± 3.25
(85/85)Gemini 3.7 Flash
0.00%± 3.03
(85/85)MedCode *
Claude Sonnet 5
0.00%± 2.27
(107/107)Gemini 3.7 Flash
0.00%± 2.12
(107/107)Terminal-Bench-Science
Claude Sonnet 5
0.00%± 2.79
(45/45)Gemini 3.7 Flash
0.00%± 3.10
(45/45)Terminal-Bench 4.0
Claude Sonnet 5
0.00%± 1.51
(64/64)Gemini 3.7 Flash
0.00%± 3.03
(64/64)Vibe Code Bench v1.1 *
Claude Sonnet 5
0.00%± 3.05
(128/128)Gemini 3.7 Flash
0.00%± 4.84
(128/128)Overall performance
Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, legal, and tax
•2026-11-11
Comparison by Industry
Model performance on different sections of the economy.
Legal
62.87%
vs.60.94%
Finance
58.35%
vs.54.73%
Healthcare
61.80%
vs.68.67%
Math
77.00%
vs.58.00%
Science
5.71%
vs.7.14%
Academic
86.48%
vs.91.01%
Coding
44.91%
vs.55.10%
Cyber
31.14%
vs.24.16%
Social Mobility
66.03%
vs.N/A
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
$2.00
vs.$1.50
Input Cache Write/ 1M Tokens
$2.50
vs.N/A
Input Cache Read/ 1M Tokens
$0.20
vs.$0.15
Output Cost/ 1M Tokens
$10.00
vs.$7.50
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | Anthropic | Google |
| Latency | N/A | N/A |
| Cost (In/Out) | $2 / $10 | $1.5 / $7.5 |
| Context Window | 1M | 1M |
| Max Output Token | 128k | 66k |
| Input Modality |