Compare Models
Select models (max 5)
Gemini 3.7 FlashGPT-5.6 Luna
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | 59.31%±1.06 | 59.88%±1.09 |
| Legal Research BenchAgentic US legal research | 34.62%±3.31 | 36.54%±3.35 |
| Finance Agent (v2)Core financial analyst tasks | 59.04%±0.27 | 55.04%±0.31 |
| Tax Agent BenchAgentic US corporate tax research | 57.66%±3.31 | 60.81%±3.26 |
| MedCodeMedical billing code support | 53.39%±2.12 | 42.39%±2.27 |
| Terminal-Bench ScienceExpert-authored scientific research workflows | 5.71%±2.79 | 5.71%±2.79 |
| Code MigrationRewriting programs in new languages | 34.80%±4.22 | 44.55%±4.24 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 6.06%±0.88 | 4.54%±0.88 |
| Vibe Code Bench v1.1Building web apps from scratch | 70.39%±4.84 | 77.06%±3.07 |
Benchmarks
Vals Index *
Gemini 3.7 Flash
0.00%± 1.06
(66/66)GPT-5.6 Luna
0.00%± 1.09
(66/66)Legal Research Bench *
Gemini 3.7 Flash
0.00%± 3.31
(69/69)GPT-5.6 Luna
0.00%± 3.35
(69/69)Finance Agent (v2) *
Gemini 3.7 Flash
0.00%± 0.27
(70/70)GPT-5.6 Luna
0.00%± 0.31
(70/70)Tax Agent Bench *
Gemini 3.7 Flash
0.00%± 3.31
(61/61)GPT-5.6 Luna
0.00%± 3.26
(61/61)MedCode *
Gemini 3.7 Flash
0.00%± 2.12
(102/102)GPT-5.6 Luna
0.00%± 2.27
(102/102)Terminal-Bench Science
Gemini 3.7 Flash
0.00%± 2.79
(33/33)GPT-5.6 Luna
0.00%± 2.79
(33/33)Code Migration *
Gemini 3.7 Flash
0.00%± 4.22
(69/69)GPT-5.6 Luna
0.00%± 4.24
(69/69)Terminal-Bench 4.0
Gemini 3.7 Flash
0.00%± 0.88
(37/37)GPT-5.6 Luna
0.00%± 0.88
(37/37)Vibe Code Bench v1.1 *
Gemini 3.7 Flash
0.00%± 4.84
(104/104)GPT-5.6 Luna
0.00%± 3.07
(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.59.88%
Legal
43.54%
vs.40.61%
Finance
65.88%
vs.65.29%
Healthcare
68.67%
vs.63.39%
Math
58.00%
vs.60.00%
Science
5.71%
vs.27.20%
Academic
91.01%
vs.87.58%
Education
49.23%
vs.44.22%
Coding
51.80%
vs.45.50%
Beta
24.16%
vs.73.63%
Social Mobility
N/A
vs.61.16%
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
$4.17
$0.779
Cost / TestVals Index
$4.17
vs.$0.779
Input Cost/ 1M Tokens
$1.50
vs.$0.20
Input Cache Write/ 1M Tokens
N/A
vs.$0.25
Input Cache Read/ 1M Tokens
$0.15
vs.$0.02
Output Cost/ 1M Tokens
$7.50
vs.$1.20
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | Google | OpenAI |
| Latency | 2592.93s | 1396.33s |
| Cost (In/Out) | $1.5 / $7.5 | $0.2 / $1.2 |
| Context Window | 1M | 1M |
| Max Output Token | 66k | 128k |
| Input Modality |