Compare Models
Select models (max 7)
Gemini 3 Flash (12/25)Gemini 3 Pro (11/25)
 |  | |
|---|---|---|
| Legal Research BenchAgentic US legal research | 18.27%±2.69 | N/A |
| Tax Agent BenchAgentic US corporate tax research | 11.84%±2.32 | N/A |
| MedCodeMedical billing code support | 55.92%±2.11 | 52.20%±2.07 |
| Vibe Code Bench v1.1Building web apps from scratch | 20.20%±3.95 | 14.30%±3.06 |
Benchmarks
Legal Research Bench *
Gemini 3 Flash (12/25)
0.00%± 2.69
(93/93)Gemini 3 Pro (11/25)
N/ATax Agent Bench *
Gemini 3 Flash (12/25)
0.00%± 2.32
(84/84)Gemini 3 Pro (11/25)
N/AMedCode *
Gemini 3 Flash (12/25)
0.00%± 2.11
(107/107)Gemini 3 Pro (11/25)
0.00%± 2.07
(107/107)Vibe Code Bench v1.1 *
Gemini 3 Flash (12/25)
0.00%± 3.95
(127/127)Gemini 3 Pro (11/25)
0.00%± 3.06
(127/127)Overall performance
Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, legal, and tax
•2026-11-09
Comparison by Industry
Model performance on different sections of the economy.
Legal
52.56%
vs.87.03%
Finance
51.48%
vs.70.82%
Healthcare
62.92%
vs.62.12%
Academic
88.03%
vs.89.76%
Coding
45.20%
vs.59.04%
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
N/A
N/A
Cost / TestVals Index
N/A
vs.N/A
Input Cost/ 1M Tokens
$0.50
vs.$2.00
Input Cache Read/ 1M Tokens
$0.05
vs.$0.20
Output Cost/ 1M Tokens
$3.00
vs.$12.00
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | Google | Google |
| Latency | N/A | N/A |
| Cost (In/Out) | $0.5 / $3 | $2 / $12 |
| Context Window | 1M | 1M |
| Max Output Token | 66k | 66k |
| Input Modality |