Compare Models
Select models (max 7)
Gemini 3.1 Pro Preview (02/26)Inkling Small
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | N/A | 27.59%±1.13 |
| Legal Research BenchAgentic US legal research | 20.67%±2.81 | 25.48%±3.03 |
| Finance Agent v2.1Core financial analyst tasks | N/A | 44.78%±2.10 |
| Tax Agent BenchAgentic US corporate tax research | 9.29%±2.09 | 15.39%±2.37 |
| MedCodeMedical billing code support | 59.06%±2.00 | 37.89%±2.21 |
| Terminal-Bench-ScienceExpert-authored scientific research workflows | 1.43%±1.43 | N/A |
| Code Migration v1.1Rewriting programs in new languages | N/A | 10.43%±2.32 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 2.52%±0.51 | 0.00%±0.00 |
| Vibe Code Bench v1.1Building web apps from scratch | 32.03%±4.34 | 19.05%±3.40 |
Benchmarks
Vals Index *
Gemini 3.1 Pro Preview (02/26)
N/AInkling Small
0.00%± 1.13
(26/26)Legal Research Bench *
Gemini 3.1 Pro Preview (02/26)
0.00%± 2.81
(84/84)Inkling Small
0.00%± 3.03
(84/84)Finance Agent v2.1 *
Gemini 3.1 Pro Preview (02/26)
N/AInkling Small
0.00%± 2.10
(30/30)Tax Agent Bench *
Gemini 3.1 Pro Preview (02/26)
0.00%± 2.09
(75/75)Inkling Small
0.00%± 2.37
(75/75)MedCode *
Gemini 3.1 Pro Preview (02/26)
0.00%± 2.00
(107/107)Inkling Small
0.00%± 2.21
(107/107)Terminal-Bench-Science
Gemini 3.1 Pro Preview (02/26)
0.00%± 1.43
(42/42)Inkling Small
N/ACode Migration v1.1 *
Gemini 3.1 Pro Preview (02/26)
N/AInkling Small
0.00%± 2.32
(28/28)Terminal-Bench 4.0
Gemini 3.1 Pro Preview (02/26)
0.00%± 0.51
(54/54)Inkling Small
0.00%± 0.00
(54/54)Vibe Code Bench v1.1 *
Gemini 3.1 Pro Preview (02/26)
0.00%± 4.34
(118/118)Inkling Small
0.00%± 3.40
(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
54.04%
vs.37.13%
Finance
50.52%
vs.47.76%
Healthcare
67.59%
vs.61.00%
Math
26.00%
vs.6.00%
Science
27.38%
vs.N/A
Academic
91.55%
vs.84.58%
Education
48.68%
vs.32.74%
Coding
37.20%
vs.30.13%
Cyber
0.00%
vs.64.11%
Social Mobility
53.79%
vs.59.41%
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
N/A
$0.401
Cost / TestVals Index
N/A
vs.$0.401
Input Cost/ 1M Tokens
$2.00
vs.$0.30
Input Cache Read/ 1M Tokens
$0.20
vs.$0.06
Output Cost/ 1M Tokens
$12.00
vs.$1.20
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | Google | Thinking Machines |
| Latency | N/A | 986.44s |
| Cost (In/Out) | $2 / $12 | $0.3 / $1.2 |
| Context Window | 1M | 262k |
| Max Output Token | 66k | 262k |
| Input Modality |