Compare Models
Select models (max 7)
Inkling SmallMistral Large 4 OSS
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | 27.59%±1.13 | 56.42%±1.26 |
| Legal Research BenchAgentic US legal research | 25.48%±3.03 | 35.58%±3.33 |
| Finance Agent v2.1Core financial analyst tasks | 44.78%±2.10 | 61.72%±2.05 |
| Tax Agent BenchAgentic US corporate tax research | 15.39%±2.37 | 27.33%±2.95 |
| MedCodeMedical billing code support | 37.89%±2.21 | N/A |
| Code Migration v1.1Rewriting programs in new languages | 10.43%±2.32 | N/A |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 0.00%±0.00 | 26.26%±5.13 |
| Vibe Code Bench v1.1Building web apps from scratch | 19.05%±3.40 | 81.56%±3.29 |
Benchmarks
Vals Index *
Inkling Small
0.00%± 1.13
(32/32)Mistral Large 4 OSS
0.00%± 1.26
(32/32)Legal Research Bench *
Inkling Small
0.00%± 3.03
(89/89)Mistral Large 4 OSS
0.00%± 3.33
(89/89)Finance Agent v2.1 *
Inkling Small
0.00%± 2.10
(35/35)Mistral Large 4 OSS
0.00%± 2.05
(35/35)Tax Agent Bench *
Inkling Small
0.00%± 2.37
(80/80)Mistral Large 4 OSS
0.00%± 2.95
(80/80)MedCode *
Inkling Small
0.00%± 2.21
(107/107)Mistral Large 4 OSS
N/ACode Migration v1.1 *
Inkling Small
0.00%± 2.32
(29/29)Mistral Large 4 OSS
N/ATerminal-Bench 4.0
Inkling Small
0.00%± 0.00
(59/59)Mistral Large 4 OSS
0.00%± 5.13
(59/59)Vibe Code Bench v1.1 *
Inkling Small
0.00%± 3.40
(123/123)Mistral Large 4 OSS
0.00%± 3.29
(123/123)Overall performance
Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, and law
•2026-10-29
Comparison by Industry
Model performance on different sections of the economy.
Legal
37.13%
vs.25.70%
Finance
47.76%
vs.52.58%
Healthcare
61.00%
vs.N/A
Math
6.00%
vs.N/A
Academic
84.58%
vs.N/A
Coding
30.13%
vs.53.91%
Cyber
64.11%
vs.N/A
Social Mobility
59.41%
vs.N/A
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
$0.401
$3.717
Cost / TestVals Index
$0.401
vs.$3.717
Input Cost/ 1M Tokens
$0.30
vs.$0.70
Input Cache Read/ 1M Tokens
$0.06
vs.$0.07
Output Cost/ 1M Tokens
$1.20
vs.$2.10
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | Thinking Machines | Mistral AI |
| Latency | 986.44s | 2868.04s |
| Cost (In/Out) | $0.3 / $1.2 | $0.7 / $2.1 |
| Context Window | 262k | 1M |
| Max Output Token | 262k | 256k |
| Input Modality |