Compare Models
Select models (max 7)
Gemini 3.8 FlashGPT-5.6 Terra
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | 55.95%±1.14 | N/A |
| Legal Research BenchAgentic US legal research | 38.94%±3.39 | 41.35%±3.42 |
| Finance Agent v2.1Core financial analyst tasks | 65.76%±2.04 | N/A |
| Tax Agent BenchAgentic US corporate tax research | 32.12%±3.37 | 30.04%±3.31 |
| MedCodeMedical billing code support | 48.13%±2.18 | 43.41%±2.17 |
| Terminal-Bench-ScienceExpert-authored scientific research workflows | 8.57%±3.37 | 10.00%±3.61 |
| Code Migration v1.1Rewriting programs in new languages | 38.65%±3.65 | N/A |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 19.70%±2.31 | 22.73%±2.31 |
| Vibe Code Bench v1.1Building web apps from scratch | 78.65%±3.88 | 74.59%±4.20 |
Benchmarks
Vals Index *
Gemini 3.8 Flash
0.00%± 1.14
(26/26)GPT-5.6 Terra
N/ALegal Research Bench *
Gemini 3.8 Flash
0.00%± 3.39
(84/84)GPT-5.6 Terra
0.00%± 3.42
(84/84)Finance Agent v2.1 *
Gemini 3.8 Flash
0.00%± 2.04
(30/30)GPT-5.6 Terra
N/ATax Agent Bench *
Gemini 3.8 Flash
0.00%± 3.37
(75/75)GPT-5.6 Terra
0.00%± 3.31
(75/75)MedCode *
Gemini 3.8 Flash
0.00%± 2.18
(107/107)GPT-5.6 Terra
0.00%± 2.17
(107/107)Terminal-Bench-Science
Gemini 3.8 Flash
0.00%± 3.37
(42/42)GPT-5.6 Terra
0.00%± 3.61
(42/42)Code Migration v1.1 *
Gemini 3.8 Flash
0.00%± 3.65
(28/28)GPT-5.6 Terra
N/ATerminal-Bench 4.0
Gemini 3.8 Flash
0.00%± 2.31
(54/54)GPT-5.6 Terra
0.00%± 2.31
(54/54)Vibe Code Bench v1.1 *
Gemini 3.8 Flash
0.00%± 3.88
(118/118)GPT-5.6 Terra
0.00%± 4.20
(118/118)Overall performance
Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, and law
•2026-10-22
Comparison by Industry
Model performance on different sections of the economy.
Legal
46.01%
vs.63.23%
Finance
62.11%
vs.57.84%
Healthcare
66.32%
vs.63.14%
Math
48.00%
vs.74.00%
Science
35.76%
vs.10.00%
Academic
91.25%
vs.88.01%
Education
35.06%
vs.47.00%
Coding
48.20%
vs.55.06%
Cyber
27.41%
vs.40.81%
Social Mobility
65.29%
vs.62.38%
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
$6.065
N/A
Cost / TestVals Index
$6.065
vs.N/A
Input Cost/ 1M Tokens
$1.50
vs.$2.00
Input Cache Write/ 1M Tokens
N/A
vs.$2.50
Input Cache Read/ 1M Tokens
$0.15
vs.$0.20
Output Cost/ 1M Tokens
$7.50
vs.$12.00
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | Google | OpenAI |
| Latency | 2158.48s | N/A |
| Cost (In/Out) | $1.5 / $7.5 | $2 / $12 |
| Context Window | 1M | 1M |
| Max Output Token | 66k | 128k |
| Input Modality |