Compare Models
Select models (max 5)
Grok 4.20 (Reasoning)GPT-6.1 Sol
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | N/A | 61.15%±1.01 |
| Legal Research BenchAgentic US legal research | 13.94%±2.41 | 38.46%±3.38 |
| Finance Agent (v2)Core financial analyst tasks | 28.49%±0.32 | 52.03%±0.31 |
| Tax Agent BenchAgentic US corporate tax research | 31.24%±2.70 | 62.31%±3.20 |
| MedCodeMedical billing code support | 32.16%±2.12 | 48.84%±2.12 |
| Code MigrationRewriting programs in new languages | 0.31%±0.11 | 65.12%±4.36 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | N/A | 55.05%±1.82 |
| Vibe Code Bench v1.1Building web apps from scratch | 4.06%±2.06 | 88.93%±1.89 |
Benchmarks
Vals Index *
Grok 4.20 (Reasoning)
N/AGPT-6.1 Sol
0.00%± 1.01
(30/30)Legal Research Bench *
Grok 4.20 (Reasoning)
0.00%± 2.41
(71/71)GPT-6.1 Sol
0.00%± 3.38
(71/71)Finance Agent (v2) *
Grok 4.20 (Reasoning)
0.00%± 0.32
(72/72)GPT-6.1 Sol
0.00%± 0.31
(72/72)Tax Agent Bench *
Grok 4.20 (Reasoning)
0.00%± 2.70
(63/63)GPT-6.1 Sol
0.00%± 3.20
(63/63)MedCode *
Grok 4.20 (Reasoning)
0.00%± 2.12
(103/103)GPT-6.1 Sol
0.00%± 2.12
(103/103)Code Migration *
Grok 4.20 (Reasoning)
0.00%± 0.11
(70/70)GPT-6.1 Sol
0.00%± 4.36
(70/70)Terminal-Bench 4.0
Grok 4.20 (Reasoning)
N/AGPT-6.1 Sol
0.00%± 1.82
(31/31)Vibe Code Bench v1.1 *
Grok 4.20 (Reasoning)
0.00%± 2.06
(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
30.56%
vs.21.94%
Finance
38.19%
vs.61.71%
Healthcare
47.78%
vs.67.65%
Math
N/A
vs.99.00%
Science
N/A
vs.63.01%
Academic
86.12%
vs.N/A
Education
38.24%
vs.46.54%
Coding
40.21%
vs.76.50%
Beta
N/A
vs.45.02%
Social Mobility
N/A
vs.59.34%
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
N/A
$3.237
Cost / TestVals Index
N/A
vs.$3.237
Input Cost/ 1M Tokens
$2.00
vs.$2.00
Input Cache Write/ 1M Tokens
N/A
vs.$2.50
Input Cache Read/ 1M Tokens
$0.20
vs.$0.10
Output Cost/ 1M Tokens
$6.00
vs.$10.00
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | SpaceXAI | OpenAI |
| Latency | N/A | 2590.01s |
| Cost (In/Out) | $2 / $6 | $2 / $10 |
| Context Window | 2M | 1M |
| Max Output Token | 2M | 128k |
| Input Modality |