Compare Models
Select models (max 5)
Claude Sonnet 5GPT-6.1 Sol
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | 51.77%±1.09 | 61.15%±1.01 |
| Legal Research BenchAgentic US legal research | 41.83%±3.43 | 38.46%±3.38 |
| Finance Agent (v2)Core financial analyst tasks | 53.91%±0.52 | 52.03%±0.31 |
| Tax Agent BenchAgentic US corporate tax research | 62.27%±3.19 | 62.31%±3.20 |
| MedCodeMedical billing code support | 47.54%±2.27 | 48.84%±2.12 |
| Terminal-Bench ScienceExpert-authored scientific research workflows | 2.86%±2.01 | N/A |
| Code MigrationRewriting programs in new languages | 44.39%±4.25 | 65.12%±4.36 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 9.60%±1.01 | 55.05%±1.82 |
| Vibe Code Bench v1.1Building web apps from scratch | 81.33%±3.05 | 88.93%±1.89 |
Benchmarks
Vals Index *
Claude Sonnet 5
0.00%± 1.09
(30/30)GPT-6.1 Sol
0.00%± 1.01
(30/30)Legal Research Bench *
Claude Sonnet 5
0.00%± 3.43
(71/71)GPT-6.1 Sol
0.00%± 3.38
(71/71)Finance Agent (v2) *
Claude Sonnet 5
0.00%± 0.52
(72/72)GPT-6.1 Sol
0.00%± 0.31
(72/72)Tax Agent Bench *
Claude Sonnet 5
0.00%± 3.19
(63/63)GPT-6.1 Sol
0.00%± 3.20
(63/63)MedCode *
Claude Sonnet 5
0.00%± 2.27
(103/103)GPT-6.1 Sol
0.00%± 2.12
(103/103)Terminal-Bench Science
Claude Sonnet 5
0.00%± 2.01
(33/33)GPT-6.1 Sol
N/ACode Migration *
Claude Sonnet 5
0.00%± 4.25
(70/70)GPT-6.1 Sol
0.00%± 4.36
(70/70)Terminal-Bench 4.0
Claude Sonnet 5
0.00%± 1.01
(31/31)GPT-6.1 Sol
0.00%± 1.82
(31/31)Vibe Code Bench v1.1 *
Claude Sonnet 5
0.00%± 3.05
(105/105)GPT-6.1 Sol
0.00%± 1.89
(105/105)Overall performance
Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, and law
•2026-09-29
Comparison by Industry
Model performance on different sections of the economy.
Legal
43.58%
vs.21.94%
Finance
65.63%
vs.61.71%
Healthcare
61.80%
vs.67.65%
Math
77.00%
vs.99.00%
Science
2.86%
vs.63.01%
Academic
86.48%
vs.N/A
Education
48.92%
vs.46.54%
Coding
44.74%
vs.76.50%
Beta
61.91%
vs.45.02%
Social Mobility
66.03%
vs.59.34%
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
$13.72
$3.237
Cost / TestVals Index
$13.72
vs.$3.237
Input Cost/ 1M Tokens
$2.00
vs.$2.00
Input Cache Write/ 1M Tokens
$2.50
vs.$2.50
Input Cache Read/ 1M Tokens
$0.20
vs.$0.10
Output Cost/ 1M Tokens
$10.00
vs.$10.00
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | Anthropic | OpenAI |
| Latency | 3255.62s | 2590.01s |
| Cost (In/Out) | $2 / $10 | $2 / $10 |
| Context Window | 1M | 1M |
| Max Output Token | 128k | 128k |
| Input Modality |