Compare Models
Select models (max 5)
Gemini 3.6 FlashKimi K3
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | N/A | 50.30%±0.99 |
| Legal Research BenchAgentic US legal research | 25.00%±3.01 | 46.15%±3.46 |
| Finance Agent (v2)Core financial analyst tasks | 56.30%±0.18 | 53.11%±0.37 |
| Tax Agent BenchAgentic US corporate tax research | 49.90%±3.30 | 68.67%±3.08 |
| MedCodeMedical billing code support | 53.15%±2.16 | 49.36%±2.20 |
| Terminal-Bench ScienceExpert-authored scientific research workflows | 4.29%±2.44 | 1.43%±1.43 |
| Code MigrationRewriting programs in new languages | 30.93%±4.07 | 16.10%±4.10 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | N/A | 17.17%±0.51 |
| Vibe Code Bench v1.1Building web apps from scratch | 64.00%±4.29 | 84.97%±2.75 |
Benchmarks
Vals Index *
Gemini 3.6 Flash
N/AKimi K3
0.00%± 0.99
(43/43)Legal Research Bench *
Gemini 3.6 Flash
0.00%± 3.01
(73/73)Kimi K3
0.00%± 3.46
(73/73)Finance Agent (v2) *
Gemini 3.6 Flash
0.00%± 0.18
(74/74)Kimi K3
0.00%± 0.37
(74/74)Tax Agent Bench *
Gemini 3.6 Flash
0.00%± 3.30
(65/65)Kimi K3
0.00%± 3.08
(65/65)MedCode *
Gemini 3.6 Flash
0.00%± 2.16
(104/104)Kimi K3
0.00%± 2.20
(104/104)Terminal-Bench Science
Gemini 3.6 Flash
0.00%± 2.44
(38/38)Kimi K3
0.00%± 1.43
(38/38)Code Migration *
Gemini 3.6 Flash
0.00%± 4.07
(73/73)Kimi K3
0.00%± 4.10
(73/73)Terminal-Bench 4.0
Gemini 3.6 Flash
N/AKimi K3
0.00%± 0.51
(43/43)Vibe Code Bench v1.1 *
Gemini 3.6 Flash
0.00%± 4.29
(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
38.35%
vs.48.43%
Finance
62.81%
vs.66.10%
Healthcare
66.41%
vs.68.70%
Math
N/A
vs.87.00%
Science
31.40%
vs.37.01%
Academic
90.36%
vs.89.68%
Education
48.69%
vs.52.78%
Coding
49.61%
vs.46.00%
Cyber
45.36%
vs.75.24%
Social Mobility
56.56%
vs.68.20%
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
N/A
$6.382
Cost / TestVals Index
N/A
vs.$6.382
Input Cost/ 1M Tokens
$1.50
vs.$3.00
Input Cache Read/ 1M Tokens
$0.15
vs.$0.30
Output Cost/ 1M Tokens
$7.50
vs.$15.00
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | Google | Kimi |
| Latency | N/A | 4103.02s |
| Cost (In/Out) | $1.5 / $7.5 | $3 / $15 |
| Context Window | 1M | 1M |
| Max Output Token | 66k | 1M |
| Input Modality |