Compare Models
Select models (max 5)
Gemini 3.7 FlashKimi K3
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | 59.31%±1.06 | 57.81%±1.06 |
| Legal Research BenchAgentic US legal research | 34.62%±3.31 | 44.23%±3.45 |
| Finance Agent (v2)Core financial analyst tasks | 59.04%±0.27 | 54.36%±0.53 |
| Tax Agent BenchAgentic US corporate tax research | 57.66%±3.31 | 68.67%±3.08 |
| MedCodeMedical billing code support | 53.39%±2.12 | 48.88%±2.19 |
| Terminal-Bench ScienceExpert-authored scientific research workflows | 5.71%±2.79 | 2.86%±2.01 |
| Code MigrationRewriting programs in new languages | 34.80%±4.22 | 16.10%±4.10 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 6.06%±0.88 | 12.63%±1.01 |
| Vibe Code Bench v1.1Building web apps from scratch | 70.39%±4.84 | 84.96%±2.69 |
Benchmarks
Vals Index *
Gemini 3.7 Flash
0.00%± 1.06
(66/66)Kimi K3
0.00%± 1.06
(66/66)Legal Research Bench *
Gemini 3.7 Flash
0.00%± 3.31
(69/69)Kimi K3
0.00%± 3.45
(69/69)Finance Agent (v2) *
Gemini 3.7 Flash
0.00%± 0.27
(70/70)Kimi K3
0.00%± 0.53
(70/70)Tax Agent Bench *
Gemini 3.7 Flash
0.00%± 3.31
(61/61)Kimi K3
0.00%± 3.08
(61/61)MedCode *
Gemini 3.7 Flash
0.00%± 2.12
(102/102)Kimi K3
0.00%± 2.19
(102/102)Terminal-Bench Science
Gemini 3.7 Flash
0.00%± 2.79
(33/33)Kimi K3
0.00%± 2.01
(33/33)Code Migration *
Gemini 3.7 Flash
0.00%± 4.22
(69/69)Kimi K3
0.00%± 4.10
(69/69)Terminal-Bench 4.0
Gemini 3.7 Flash
0.00%± 0.88
(37/37)Kimi K3
0.00%± 1.01
(37/37)Vibe Code Bench v1.1 *
Gemini 3.7 Flash
0.00%± 4.84
(104/104)Kimi K3
0.00%± 2.69
(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
38.79%
vs.39.35%
Legal
43.54%
vs.47.03%
Finance
65.88%
vs.66.30%
Healthcare
68.67%
vs.68.42%
Math
58.00%
vs.87.00%
Science
5.71%
vs.37.17%
Academic
91.01%
vs.89.68%
Education
49.23%
vs.54.26%
Coding
51.80%
vs.45.43%
Beta
24.16%
vs.42.87%
Social Mobility
N/A
vs.68.27%
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
$4.17
$6.468
Cost / TestVals Index
$4.17
vs.$6.468
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 | 2592.93s | 4173.70s |
| Cost (In/Out) | $1.5 / $7.5 | $3 / $15 |
| Context Window | 1M | 1M |
| Max Output Token | 66k | 1M |
| Input Modality |