Compare Models

Select models (max 7)
GPT 5.4 MiniInkling
Benchmarks

Vals Index *

GPT 5.4 Mini
N/A
Inkling
0.00%± 1.12
(41/41)

Legal Research Bench *

GPT 5.4 Mini
0.00%± 2.30
(98/98)
Inkling
0.00%± 3.13
(98/98)

Finance Agent v2.1 *

GPT 5.4 Mini
N/A
Inkling
0.00%± 2.12
(44/44)

Tax Agent Bench *

GPT 5.4 Mini
0.00%± 2.04
(89/89)
Inkling
0.00%± 2.42
(89/89)

MedCode *

GPT 5.4 Mini
N/A
Inkling
0.00%± 2.23
(107/107)

Code Migration v1.1 *

GPT 5.4 Mini
N/A
Inkling
0.00%± 2.71
(30/30)

Terminal-Bench 4.0

GPT 5.4 Mini
0.00%± 1.01
(68/68)
Inkling
0.00%± 0.51
(68/68)

Vibe Code Bench v1.1 *

GPT 5.4 Mini
0.00%± 5.61
(132/132)
Inkling
0.00%± 3.66
(132/132)

Overall performance

Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, legal, and tax

2026-11-16

Comparison by Industry

Model performance on different sections of the economy.

Legal
12.50%
38.35%
Finance
47.85%
49.09%
Healthcare
N/A
63.30%
Math
N/A
0.00%
Academic
82.29%
83.97%
Coding
40.99%
29.09%
Cyber
N/A
33.39%
Social Mobility
N/A
58.46%

Cost Analysis

Per task and per token model pricing.

Vals Index · USD
N/A
$1.848
Cost / TestVals Index
N/A
$1.848
Input Cost/ 1M Tokens
$0.75
$1.00
Input Cache Read/ 1M Tokens
$0.075
$0.17
Output Cost/ 1M Tokens
$4.50
$4.05

Model Metadata

Basic information about each model.

Model provider
OpenAIOpenAI
Thinking MachinesThinking Machines
LatencyN/A1032.92s
Cost (In/Out)$0.75 / $4.5$1 / $4.05
Context Window400k256k
Max Output Token128k256k
Input Modality