Compare Models
Select models (max 7)
GPT-5.6 TerraBison 1
| Legal Research BenchAgentic US legal research | 41.35%±3.42 | N/A |
| Tax Agent BenchAgentic US corporate tax research | 30.04%±3.31 | N/A |
| MedCodeMedical billing code support | 43.41%±2.17 | N/A |
| Terminal-Bench-ScienceExpert-authored scientific research workflows | 10.00%±3.61 | N/A |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 22.73%±2.31 | N/A |
| Vibe Code Bench v1.1Building web apps from scratch | 74.59%±4.20 | N/A |
Benchmarks
Legal Research Bench *
GPT-5.6 Terra
0.00%± 3.42
(100/100)Bison 1
N/ATax Agent Bench *
GPT-5.6 Terra
0.00%± 3.31
(91/91)Bison 1
N/AMedCode *
GPT-5.6 Terra
0.00%± 2.17
(109/109)Bison 1
N/ATerminal-Bench-Science
GPT-5.6 Terra
0.00%± 3.61
(49/49)Bison 1
N/ATerminal-Bench 4.0
GPT-5.6 Terra
0.00%± 2.31
(70/70)Bison 1
N/AVibe Code Bench v1.1 *
GPT-5.6 Terra
0.00%± 4.20
(134/134)Bison 1
N/AOverall performance
Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, legal, and tax
No selected models have a Vals Index score.
Comparison by Industry
Model performance on different sections of the economy.
Legal
63.23%
vs.N/A
Finance
57.84%
vs.99.08%
Healthcare
63.14%
vs.N/A
Math
74.00%
vs.N/A
Science
10.00%
vs.N/A
Academic
88.01%
vs.N/A
Education
87.04%
vs.N/A
Coding
60.81%
vs.N/A
Cyber
40.81%
vs.N/A
Social Mobility
66.68%
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
$2.00
vs.$0.10
Input Cache Write/ 1M Tokens
$2.50
vs.N/A
Input Cache Read/ 1M Tokens
$0.20
vs.N/A
Output Cost/ 1M Tokens
$12.00
vs.$0.00
Model Metadata
Basic information about each model.
| Model provider | ||
| Latency | N/A | N/A |
| Cost (In/Out) | $2 / $12 | $0.1 / $0 |
| Context Window | 1M | 131k |
| Max Output Token | 128k | 0 |
| Input Modality |