Compare Models
Select models (max 7)
Grok 3 Mini ReasoningGemini 4 Carbon
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | N/A | 70.36%±0.97 |
| Legal Research BenchAgentic US legal research | N/A | 55.77%±3.45 |
| Finance Agent v2.1Core financial analyst tasks | N/A | 67.16%±2.02 |
| Tax Agent BenchAgentic US corporate tax research | N/A | 48.86%±3.42 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | N/A | 63.13%±2.20 |
| Vibe Code Bench v1.1Building web apps from scratch | N/A | 89.06%±2.29 |
Benchmarks
Vals Index *
Grok 3 Mini Reasoning
N/AGemini 4 Carbon
0.00%± 0.97
(29/29)Legal Research Bench *
Grok 3 Mini Reasoning
N/AGemini 4 Carbon
0.00%± 3.45
(87/87)Finance Agent v2.1 *
Grok 3 Mini Reasoning
N/AGemini 4 Carbon
0.00%± 2.02
(33/33)Tax Agent Bench *
Grok 3 Mini Reasoning
N/AGemini 4 Carbon
0.00%± 3.42
(78/78)Terminal-Bench 4.0
Grok 3 Mini Reasoning
N/AGemini 4 Carbon
0.00%± 2.20
(57/57)Vibe Code Bench v1.1 *
Grok 3 Mini Reasoning
N/AGemini 4 Carbon
0.00%± 2.29
(121/121)Overall performance
Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, and law
•2026-10-27
Comparison by Industry
Model performance on different sections of the economy.
Legal
83.14%
vs.36.63%
Finance
71.14%
vs.64.16%
Academic
80.33%
vs.N/A
Coding
76.22%
vs.76.10%
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
N/A
$10.51
Cost / TestVals Index
N/A
vs.$10.51
Input Cost/ 1M Tokens
$0.30
vs.$4.00
Input Cache Read/ 1M Tokens
$0.075
vs.$0.20
Output Cost/ 1M Tokens
$0.50
vs.$20.00
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | SpaceXAI | Google |
| Latency | N/A | 2864.86s |
| Cost (In/Out) | $0.3 / $0.5 | $4 / $20 |
| Context Window | 131k | 1M |
| Max Output Token | 0 | 1M |
| Input Modality |