Compare Models
Select models (max 5)
Gemini 3.5 Flash LiteGPT 5.4 Nano
 |  |  |
|---|---|---|
| Legal Research BenchAgentic US legal research | 13.94%±2.41 | 6.25%±1.68 |
| Finance Agent (v2)Core financial analyst tasks | 47.44%±0.51 | 38.22%±1.19 |
| Tax Agent BenchAgentic US corporate tax research | 37.45%±3.12 | 26.58%±2.52 |
| MedCodeMedical billing code support | 43.49%±1.95 | 41.03%±2.26 |
| Code MigrationRewriting programs in new languages | 6.15%±1.71 | 14.47%±4.03 |
| Vibe Code Bench v1.1Building web apps from scratch | 37.16%±4.63 | 26.10%±5.08 |
Benchmarks
Legal Research Bench *
Gemini 3.5 Flash Lite
0.00%± 2.41
(73/73)GPT 5.4 Nano
0.00%± 1.68
(73/73)Finance Agent (v2) *
Gemini 3.5 Flash Lite
0.00%± 0.51
(74/74)GPT 5.4 Nano
0.00%± 1.19
(74/74)Tax Agent Bench *
Gemini 3.5 Flash Lite
0.00%± 3.12
(65/65)GPT 5.4 Nano
0.00%± 2.52
(65/65)MedCode *
Gemini 3.5 Flash Lite
0.00%± 1.95
(104/104)GPT 5.4 Nano
0.00%± 2.26
(104/104)Code Migration *
Gemini 3.5 Flash Lite
0.00%± 1.71
(73/73)GPT 5.4 Nano
0.00%± 4.03
(73/73)Vibe Code Bench v1.1 *
Gemini 3.5 Flash Lite
0.00%± 4.63
(108/108)GPT 5.4 Nano
0.00%± 5.08
(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
32.67%
vs.28.06%
Finance
53.88%
vs.47.21%
Healthcare
57.19%
vs.59.06%
Academic
84.42%
vs.76.09%
Education
47.30%
vs.38.08%
Coding
39.46%
vs.48.59%
Cyber
59.11%
vs.N/A
Social Mobility
51.83%
vs.N/A
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
$0.30
vs.$0.20
Input Cache Read/ 1M Tokens
$0.03
vs.$0.02
Output Cost/ 1M Tokens
$2.50
vs.$1.25
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | Google | OpenAI |
| Latency | N/A | N/A |
| Cost (In/Out) | $0.3 / $2.5 | $0.2 / $1.25 |
| Context Window | 1M | 400k |
| Max Output Token | 66k | 128k |
| Input Modality |