Compare Models
Select models (max 5)
Claude Sonnet 5.5Grok 4.7
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | 69.22%±0.96 | 60.22%±1.08 |
| Legal Research BenchAgentic US legal research | 48.08%±3.47 | 47.12%±3.47 |
| Finance Agent (v2)Core financial analyst tasks | 58.10%±0.67 | 52.25%±0.35 |
| Tax Agent BenchAgentic US corporate tax research | 73.39%±2.98 | 65.60%±3.24 |
| MedCodeMedical billing code support | 52.92%±2.12 | 49.55%±2.17 |
| Terminal-Bench ScienceExpert-authored scientific research workflows | 38.57%±5.86 | 11.43%±3.83 |
| Code MigrationRewriting programs in new languages | 69.83%±4.26 | 44.82%±4.21 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 53.03%±1.51 | 28.28%±1.34 |
| Vibe Code Bench v1.1Building web apps from scratch | 92.39%±1.26 | 86.17%±2.18 |
Benchmarks
Vals Index *
Claude Sonnet 5.5
0.00%± 0.96
(66/66)Grok 4.7
0.00%± 1.08
(66/66)Legal Research Bench *
Claude Sonnet 5.5
0.00%± 3.47
(69/69)Grok 4.7
0.00%± 3.47
(69/69)Finance Agent (v2) *
Claude Sonnet 5.5
0.00%± 0.67
(70/70)Grok 4.7
0.00%± 0.35
(70/70)Tax Agent Bench *
Claude Sonnet 5.5
0.00%± 2.98
(61/61)Grok 4.7
0.00%± 3.24
(61/61)MedCode *
Claude Sonnet 5.5
0.00%± 2.12
(102/102)Grok 4.7
0.00%± 2.17
(102/102)Terminal-Bench Science
Claude Sonnet 5.5
0.00%± 5.86
(33/33)Grok 4.7
0.00%± 3.83
(33/33)Code Migration *
Claude Sonnet 5.5
0.00%± 4.26
(69/69)Grok 4.7
0.00%± 4.21
(69/69)Terminal-Bench 4.0
Claude Sonnet 5.5
0.00%± 1.51
(37/37)Grok 4.7
0.00%± 1.34
(37/37)Vibe Code Bench v1.1 *
Claude Sonnet 5.5
0.00%± 1.26
(104/104)Grok 4.7
0.00%± 2.18
(104/104)Overall performance
Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, and law
•2026-09-27
Comparison by Industry
Model performance on different sections of the economy.
Vals Index
69.22%
vs.40.21%
Legal
25.50%
vs.48.00%
Finance
69.07%
vs.61.61%
Healthcare
72.01%
vs.69.47%
Math
100.00%
vs.26.00%
Science
56.26%
vs.35.30%
Education
51.77%
vs.40.79%
Coding
74.58%
vs.43.50%
Beta
44.87%
vs.69.46%
Social Mobility
67.19%
vs.65.63%
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
$20.80
$11.16
Cost / TestVals Index
$20.80
vs.$11.16
Input Cost/ 1M Tokens
$2.00
vs.$2.00
Input Cache Write/ 1M Tokens
$2.50
vs.N/A
Input Cache Read/ 1M Tokens
$0.20
vs.$0.50
Output Cost/ 1M Tokens
$10.00
vs.$6.00
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | Anthropic | SpaceXAI |
| Latency | 4207.12s | 1975.97s |
| Cost (In/Out) | $2 / $10 | $2 / $6 |
| Context Window | 1M | 500k |
| Max Output Token | 128k | 500k |
| Input Modality |