Compare Models
Select models (max 5)
Grok 4.6Kimi K3
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | 52.09%±1.15 | 50.30%±0.99 |
| Legal Research BenchAgentic US legal research | 48.08%±3.47 | 46.15%±3.46 |
| Finance Agent (v2)Core financial analyst tasks | 53.68%±0.67 | 53.11%±0.37 |
| Tax Agent BenchAgentic US corporate tax research | 70.79%±3.00 | 68.67%±3.08 |
| MedCodeMedical billing code support | 44.71%±2.26 | 49.36%±2.20 |
| Terminal-Bench ScienceExpert-authored scientific research workflows | 11.43%±3.83 | 1.43%±1.43 |
| Code MigrationRewriting programs in new languages | 44.57%±4.48 | 16.10%±4.10 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 17.17%±1.34 | 17.17%±0.51 |
| Vibe Code Bench v1.1Building web apps from scratch | 76.24%±3.82 | 84.97%±2.75 |
Benchmarks
Vals Index *
Grok 4.6
0.00%± 1.15
(43/43)Kimi K3
0.00%± 0.99
(43/43)Legal Research Bench *
Grok 4.6
0.00%± 3.47
(73/73)Kimi K3
0.00%± 3.46
(73/73)Finance Agent (v2) *
Grok 4.6
0.00%± 0.67
(74/74)Kimi K3
0.00%± 0.37
(74/74)Tax Agent Bench *
Grok 4.6
0.00%± 3.00
(65/65)Kimi K3
0.00%± 3.08
(65/65)MedCode *
Grok 4.6
0.00%± 2.26
(104/104)Kimi K3
0.00%± 2.20
(104/104)Terminal-Bench Science
Grok 4.6
0.00%± 3.83
(38/38)Kimi K3
0.00%± 1.43
(38/38)Code Migration *
Grok 4.6
0.00%± 4.48
(73/73)Kimi K3
0.00%± 4.10
(73/73)Terminal-Bench 4.0
Grok 4.6
0.00%± 1.34
(43/43)Kimi K3
0.00%± 0.51
(43/43)Vibe Code Bench v1.1 *
Grok 4.6
0.00%± 3.82
(108/108)Kimi K3
0.00%± 2.75
(108/108)Overall performance
Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, and law
•2026-10-02
Comparison by Industry
Model performance on different sections of the economy.
Legal
50.07%
vs.48.43%
Finance
64.50%
vs.66.10%
Healthcare
65.62%
vs.68.70%
Math
51.00%
vs.87.00%
Science
38.09%
vs.37.01%
Academic
92.05%
vs.89.68%
Education
28.90%
vs.52.78%
Coding
48.99%
vs.46.00%
Cyber
67.68%
vs.75.24%
Social Mobility
66.85%
vs.68.20%
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
$4.493
$6.382
Cost / TestVals Index
$4.493
vs.$6.382
Input Cost/ 1M Tokens
$2.00
vs.$3.00
Input Cache Read/ 1M Tokens
$0.50
vs.$0.30
Output Cost/ 1M Tokens
$6.00
vs.$15.00
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | SpaceXAI | Kimi |
| Latency | 2221.07s | 4103.02s |
| Cost (In/Out) | $2 / $6 | $3 / $15 |
| Context Window | 500k | 1M |
| Max Output Token | 500k | 1M |
| Input Modality |