Compare Models
Select models (max 7)
Claude Opus 5.5Gemini 4 Argon
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | 70.18%±1.00 | 69.24%±1.09 |
| Legal Research BenchAgentic US legal research | 50.48%±3.48 | 54.81%±3.46 |
| Finance Agent v2.1Core financial analyst tasks | 67.85%±2.05 | 67.66%±2.00 |
| Tax Agent BenchAgentic US corporate tax research | 45.57%±3.59 | 44.56%±3.59 |
| MedCodeMedical billing code support | 49.80%±2.27 | 58.80%±2.10 |
| Terminal-Bench-ScienceExpert-authored scientific research workflows | 47.14%±6.01 | 44.29%±5.98 |
| Code Migration v1.1Rewriting programs in new languages | 81.01%±3.21 | 70.80%±3.72 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 65.15%±0.00 | 57.58%±2.31 |
| Vibe Code Bench v1.1Building web apps from scratch | 90.29%±1.53 | 91.91%±1.90 |
Benchmarks
Vals Index *
Claude Opus 5.5
0.00%± 1.00
(26/26)Gemini 4 Argon
0.00%± 1.09
(26/26)Legal Research Bench *
Claude Opus 5.5
0.00%± 3.48
(84/84)Gemini 4 Argon
0.00%± 3.46
(84/84)Finance Agent v2.1 *
Claude Opus 5.5
0.00%± 2.05
(30/30)Gemini 4 Argon
0.00%± 2.00
(30/30)Tax Agent Bench *
Claude Opus 5.5
0.00%± 3.59
(75/75)Gemini 4 Argon
0.00%± 3.59
(75/75)MedCode *
Claude Opus 5.5
0.00%± 2.27
(107/107)Gemini 4 Argon
0.00%± 2.10
(107/107)Terminal-Bench-Science
Claude Opus 5.5
0.00%± 6.01
(42/42)Gemini 4 Argon
0.00%± 5.98
(42/42)Code Migration v1.1 *
Claude Opus 5.5
0.00%± 3.21
(28/28)Gemini 4 Argon
0.00%± 3.72
(28/28)Terminal-Bench 4.0
Claude Opus 5.5
0.00%± 0.00
(54/54)Gemini 4 Argon
0.00%± 2.31
(54/54)Vibe Code Bench v1.1 *
Claude Opus 5.5
0.00%± 1.53
(118/118)Gemini 4 Argon
0.00%± 1.90
(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
29.82%
vs.56.73%
Finance
72.31%
vs.62.35%
Healthcare
70.61%
vs.73.11%
Math
100.00%
vs.99.00%
Science
47.63%
vs.41.73%
Education
45.83%
vs.53.65%
Coding
64.37%
vs.57.15%
Cyber
44.47%
vs.61.07%
Social Mobility
70.64%
vs.69.76%
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
$28.12
$13.37
Cost / TestVals Index
$28.12
vs.$13.37
Input Cost/ 1M Tokens
$4.00
vs.$4.00
Input Cache Write/ 1M Tokens
$5.00
vs.N/A
Input Cache Read/ 1M Tokens
$0.20
vs.$0.20
Output Cost/ 1M Tokens
$20.00
vs.$20.00
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | Anthropic | Google |
| Latency | 5071.09s | 2697.95s |
| Cost (In/Out) | $4 / $20 | $4 / $20 |
| Context Window | 1M | 1M |
| Max Output Token | 128k | 262k |
| Input Modality |