Compare Models
Select models (max 5)
GPT-6.1 SolClaude Sonnet 5.5
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | 61.15%±1.01 | 67.04%±0.92 |
| Legal Research BenchAgentic US legal research | 38.46%±3.38 | 48.08%±3.47 |
| Finance Agent (v2)Core financial analyst tasks | 52.03%±0.31 | 58.10%±0.67 |
| Tax Agent BenchAgentic US corporate tax research | 62.31%±3.20 | 73.39%±2.98 |
| MedCodeMedical billing code support | 48.84%±2.12 | 52.92%±2.12 |
| Terminal-Bench ScienceExpert-authored scientific research workflows | N/A | 38.57%±5.86 |
| Code MigrationRewriting programs in new languages | 65.12%±4.36 | 69.83%±4.26 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 55.05%±1.82 | 64.14%±1.01 |
| Vibe Code Bench v1.1Building web apps from scratch | 88.93%±1.89 | 92.39%±1.26 |
Benchmarks
Vals Index *
GPT-6.1 Sol
0.00%± 1.01
(30/30)Claude Sonnet 5.5
0.00%± 0.92
(30/30)Legal Research Bench *
GPT-6.1 Sol
0.00%± 3.38
(71/71)Claude Sonnet 5.5
0.00%± 3.47
(71/71)Finance Agent (v2) *
GPT-6.1 Sol
0.00%± 0.31
(72/72)Claude Sonnet 5.5
0.00%± 0.67
(72/72)Tax Agent Bench *
GPT-6.1 Sol
0.00%± 3.20
(63/63)Claude Sonnet 5.5
0.00%± 2.98
(63/63)MedCode *
GPT-6.1 Sol
0.00%± 2.12
(103/103)Claude Sonnet 5.5
0.00%± 2.12
(103/103)Terminal-Bench Science
GPT-6.1 Sol
N/AClaude Sonnet 5.5
0.00%± 5.86
(33/33)Code Migration *
GPT-6.1 Sol
0.00%± 4.36
(70/70)Claude Sonnet 5.5
0.00%± 4.26
(70/70)Terminal-Bench 4.0
GPT-6.1 Sol
0.00%± 1.82
(31/31)Claude Sonnet 5.5
0.00%± 1.01
(31/31)Vibe Code Bench v1.1 *
GPT-6.1 Sol
0.00%± 1.89
(105/105)Claude Sonnet 5.5
0.00%± 1.26
(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
21.94%
vs.25.50%
Finance
61.71%
vs.69.07%
Healthcare
67.65%
vs.72.01%
Math
99.00%
vs.100.00%
Science
63.01%
vs.56.26%
Education
46.54%
vs.51.77%
Coding
76.50%
vs.77.35%
Beta
45.02%
vs.44.87%
Social Mobility
59.34%
vs.67.19%
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
$3.237
$21.34
Cost / TestVals Index
$3.237
vs.$21.34
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.$0.20
Output Cost/ 1M Tokens
$10.00
vs.$10.00
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | OpenAI | Anthropic |
| Latency | 2590.01s | 4684.19s |
| Cost (In/Out) | $2 / $10 | $2 / $10 |
| Context Window | 1M | 1M |
| Max Output Token | 128k | 128k |
| Input Modality |