Compare Models
Select models (max 7)
Claude Sonnet 5.5GPT-6.1 Sol
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | 70.85%±0.93 | 63.94%±1.07 |
| Legal Research BenchAgentic US legal research | 48.08%±3.47 | 38.46%±3.38 |
| Finance Agent v2.1Core financial analyst tasks | 67.28%±2.02 | 61.82%±2.11 |
| Tax Agent BenchAgentic US corporate tax research | 41.96%±3.56 | 21.75%±2.98 |
| MedCodeMedical billing code support | 52.92%±2.12 | 48.84%±2.12 |
| Terminal-Bench-ScienceExpert-authored scientific research workflows | 47.14%±6.01 | 52.86%±6.01 |
| Code Migration v1.1Rewriting programs in new languages | 86.88%±1.52 | 77.32%±2.98 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 64.14%±1.01 | 55.05%±1.82 |
| Vibe Code Bench v1.1Building web apps from scratch | 92.39%±1.26 | 88.93%±1.89 |
Benchmarks
Vals Index *
Claude Sonnet 5.5
0.00%± 0.93
(26/26)GPT-6.1 Sol
0.00%± 1.07
(26/26)Legal Research Bench *
Claude Sonnet 5.5
0.00%± 3.47
(84/84)GPT-6.1 Sol
0.00%± 3.38
(84/84)Finance Agent v2.1 *
Claude Sonnet 5.5
0.00%± 2.02
(30/30)GPT-6.1 Sol
0.00%± 2.11
(30/30)Tax Agent Bench *
Claude Sonnet 5.5
0.00%± 3.56
(75/75)GPT-6.1 Sol
0.00%± 2.98
(75/75)MedCode *
Claude Sonnet 5.5
0.00%± 2.12
(107/107)GPT-6.1 Sol
0.00%± 2.12
(107/107)Terminal-Bench-Science
Claude Sonnet 5.5
0.00%± 6.01
(42/42)GPT-6.1 Sol
0.00%± 6.01
(42/42)Code Migration v1.1 *
Claude Sonnet 5.5
0.00%± 1.52
(28/28)GPT-6.1 Sol
0.00%± 2.98
(28/28)Terminal-Bench 4.0
Claude Sonnet 5.5
0.00%± 1.01
(54/54)GPT-6.1 Sol
0.00%± 1.82
(54/54)Vibe Code Bench v1.1 *
Claude Sonnet 5.5
0.00%± 1.26
(118/118)GPT-6.1 Sol
0.00%± 1.89
(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
29.25%
vs.22.36%
Finance
71.28%
vs.63.66%
Healthcare
72.01%
vs.67.65%
Math
100.00%
vs.99.00%
Science
59.12%
vs.51.80%
Education
51.77%
vs.46.54%
Coding
65.22%
vs.60.79%
Cyber
44.87%
vs.45.02%
Social Mobility
67.19%
vs.59.34%
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
$18.70
$3.614
Cost / TestVals Index
$18.70
vs.$3.614
Input Cost/ 1M Tokens
$2.00
vs.$2.00
Input Cache Write/ 1M Tokens
$2.50
vs.$2.50
Input Cache Read/ 1M Tokens
$0.10
vs.$0.10
Output Cost/ 1M Tokens
$10.00
vs.$10.00
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | Anthropic | OpenAI |
| Latency | 5158.77s | 2664.03s |
| Cost (In/Out) | $2 / $10 | $2 / $10 |
| Context Window | 1M | 1M |
| Max Output Token | 128k | 128k |
| Input Modality |