Compare Models
Select models (max 7)
GPT 5.4 MiniInkling Small
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | N/A | 27.59%±1.13 |
| Legal Research BenchAgentic US legal research | 12.50%±2.30 | 25.48%±3.03 |
| Finance Agent v2.1Core financial analyst tasks | N/A | 44.78%±2.10 |
| Tax Agent BenchAgentic US corporate tax research | 8.81%±2.04 | 15.39%±2.37 |
| MedCodeMedical billing code support | N/A | 37.89%±2.21 |
| Code Migration v1.1Rewriting programs in new languages | N/A | 10.43%±2.32 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 2.52%±1.01 | 0.00%±0.00 |
| Vibe Code Bench v1.1Building web apps from scratch | 47.97%±5.61 | 19.05%±3.40 |
Benchmarks
Vals Index *
GPT 5.4 Mini
N/AInkling Small
0.00%± 1.13
(26/26)Legal Research Bench *
GPT 5.4 Mini
0.00%± 2.30
(84/84)Inkling Small
0.00%± 3.03
(84/84)Finance Agent v2.1 *
GPT 5.4 Mini
N/AInkling Small
0.00%± 2.10
(30/30)Tax Agent Bench *
GPT 5.4 Mini
0.00%± 2.04
(75/75)Inkling Small
0.00%± 2.37
(75/75)MedCode *
GPT 5.4 Mini
N/AInkling Small
0.00%± 2.21
(107/107)Code Migration v1.1 *
GPT 5.4 Mini
N/AInkling Small
0.00%± 2.32
(28/28)Terminal-Bench 4.0
GPT 5.4 Mini
0.00%± 1.01
(54/54)Inkling Small
0.00%± 0.00
(54/54)Vibe Code Bench v1.1 *
GPT 5.4 Mini
0.00%± 5.61
(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
12.50%
vs.37.13%
Finance
47.85%
vs.47.76%
Healthcare
N/A
vs.61.00%
Math
N/A
vs.6.00%
Academic
82.29%
vs.84.58%
Education
50.81%
vs.32.74%
Coding
40.99%
vs.30.13%
Cyber
N/A
vs.64.11%
Social Mobility
N/A
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
$0.75
vs.$0.30
Input Cache Read/ 1M Tokens
$0.075
vs.$0.06
Output Cost/ 1M Tokens
$4.50
vs.$1.20
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | OpenAI | Thinking Machines |
| Latency | N/A | 986.44s |
| Cost (In/Out) | $0.75 / $4.5 | $0.3 / $1.2 |
| Context Window | 400k | 262k |
| Max Output Token | 128k | 262k |
| Input Modality |