Compare Models
Select models (max 7)
Claude Sonnet 5.5Gemini 4 Hydrogen
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | 70.85%±0.93 | 68.49%±0.99 |
| Legal Research BenchAgentic US legal research | 48.08%±3.47 | 53.85%±3.46 |
| Finance Agent v2.1Core financial analyst tasks | 67.28%±2.02 | 65.12%±2.04 |
| Tax Agent BenchAgentic US corporate tax research | 41.96%±3.56 | 52.30%±3.60 |
| MedCodeMedical billing code support | 52.92%±2.12 | N/A |
| Terminal-Bench-ScienceExpert-authored scientific research workflows | 47.14%±6.01 | N/A |
| Code Migration v1.1Rewriting programs in new languages | 86.88%±1.52 | N/A |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 64.14%±1.01 | 54.04%±3.31 |
| Vibe Code Bench v1.1Building web apps from scratch | 92.39%±1.26 | 87.78%±2.29 |
Benchmarks
Vals Index *
Claude Sonnet 5.5
0.00%± 0.93
(37/37)Gemini 4 Hydrogen
0.00%± 0.99
(37/37)Legal Research Bench *
Claude Sonnet 5.5
0.00%± 3.47
(94/94)Gemini 4 Hydrogen
0.00%± 3.46
(94/94)Finance Agent v2.1 *
Claude Sonnet 5.5
0.00%± 2.02
(40/40)Gemini 4 Hydrogen
0.00%± 2.04
(40/40)Tax Agent Bench *
Claude Sonnet 5.5
0.00%± 3.56
(85/85)Gemini 4 Hydrogen
0.00%± 3.60
(85/85)MedCode *
Claude Sonnet 5.5
0.00%± 2.12
(107/107)Gemini 4 Hydrogen
N/ATerminal-Bench-Science
Claude Sonnet 5.5
0.00%± 6.01
(45/45)Gemini 4 Hydrogen
N/ACode Migration v1.1 *
Claude Sonnet 5.5
0.00%± 1.52
(30/30)Gemini 4 Hydrogen
N/ATerminal-Bench 4.0
Claude Sonnet 5.5
0.00%± 1.01
(64/64)Gemini 4 Hydrogen
0.00%± 3.31
(64/64)Vibe Code Bench v1.1 *
Claude Sonnet 5.5
0.00%± 1.26
(128/128)Gemini 4 Hydrogen
0.00%± 2.29
(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
42.49%
vs.32.55%
Finance
71.28%
vs.64.41%
Healthcare
72.01%
vs.N/A
Math
100.00%
vs.N/A
Science
59.12%
vs.N/A
Education
88.03%
vs.N/A
Coding
65.22%
vs.70.91%
Cyber
44.87%
vs.N/A
Social Mobility
71.06%
vs.N/A
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
$16.18
$9.838
Cost / TestVals Index
$16.18
vs.$9.838
Input Cost/ 1M Tokens
$2.00
vs.$1.50
Input Cache Write/ 1M Tokens
$2.50
vs.N/A
Input Cache Read/ 1M Tokens
$0.10
vs.$0.15
Output Cost/ 1M Tokens
$10.00
vs.$7.50
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | Anthropic | Google |
| Latency | 5158.77s | 1924.73s |
| Cost (In/Out) | $2 / $10 | $1.5 / $7.5 |
| Context Window | 1M | 1M |
| Max Output Token | 128k | 1M |
| Input Modality |