Compare Models
Select models (max 5)
Claude Sonnet 4.6Gemini 3.6 Flash
 |  |  |
|---|---|---|
| Legal Research BenchAgentic US legal research | 38.46%±3.38 | 25.00%±3.01 |
| Finance Agent (v2)Core financial analyst tasks | 51.03%±0.33 | 56.30%±0.18 |
| Tax Agent BenchAgentic US corporate tax research | 64.85%±3.11 | 49.90%±3.30 |
| MedCodeMedical billing code support | N/A | 53.15%±2.16 |
| Terminal-Bench ScienceExpert-authored scientific research workflows | N/A | 4.29%±2.44 |
| Code MigrationRewriting programs in new languages | 39.89%±4.14 | 30.93%±4.07 |
| Vibe Code Bench v1.1Building web apps from scratch | 51.48%±4.64 | 64.00%±4.29 |
Benchmarks
Legal Research Bench *
Claude Sonnet 4.6
0.00%± 3.38
(73/73)Gemini 3.6 Flash
0.00%± 3.01
(73/73)Finance Agent (v2) *
Claude Sonnet 4.6
0.00%± 0.33
(74/74)Gemini 3.6 Flash
0.00%± 0.18
(74/74)Tax Agent Bench *
Claude Sonnet 4.6
0.00%± 3.11
(65/65)Gemini 3.6 Flash
0.00%± 3.30
(65/65)MedCode *
Claude Sonnet 4.6
N/AGemini 3.6 Flash
0.00%± 2.16
(104/104)Terminal-Bench Science
Claude Sonnet 4.6
N/AGemini 3.6 Flash
0.00%± 2.44
(38/38)Code Migration *
Claude Sonnet 4.6
0.00%± 4.14
(73/73)Gemini 3.6 Flash
0.00%± 4.07
(73/73)Vibe Code Bench v1.1 *
Claude Sonnet 4.6
0.00%± 4.64
(108/108)Gemini 3.6 Flash
0.00%± 4.29
(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
41.86%
vs.38.35%
Finance
64.17%
vs.62.81%
Healthcare
N/A
vs.66.41%
Science
N/A
vs.31.40%
Academic
85.51%
vs.90.36%
Education
46.58%
vs.48.69%
Coding
50.07%
vs.49.61%
Cyber
N/A
vs.45.36%
Social Mobility
62.45%
vs.56.56%
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
$3.00
vs.$1.50
Input Cache Write/ 1M Tokens
$3.75
vs.N/A
Input Cache Read/ 1M Tokens
$0.30
vs.$0.15
Output Cost/ 1M Tokens
$15.00
vs.$7.50
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | Anthropic | Google |
| Latency | N/A | N/A |
| Cost (In/Out) | $3 / $15 | $1.5 / $7.5 |
| Context Window | 1M | 1M |
| Max Output Token | 128k | 66k |
| Input Modality |