Compare Models
Select models (max 5)
InklingWonder Full
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | 28.67%±1.10 | 64.57%±1.07 |
| Legal Research BenchAgentic US legal research | 28.36%±3.13 | 53.37%±3.47 |
| Finance Agent (v2)Core financial analyst tasks | 46.60%±0.93 | 59.06%±0.21 |
| Tax Agent BenchAgentic US corporate tax research | 15.29%±2.42 | 43.00%±3.57 |
| MedCodeMedical billing code support | 41.19%±2.23 | 49.93%±2.18 |
| Terminal-Bench ScienceExpert-authored scientific research workflows | N/A | 37.14%±5.82 |
| Code MigrationRewriting programs in new languages | 11.79%±3.40 | 61.03%±4.42 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 0.51%±0.51 | 58.08%±3.31 |
| Vibe Code Bench v1.1Building web apps from scratch | 19.21%±3.66 | 86.00%±1.93 |
Benchmarks
Vals Index *
Inkling
0.00%± 1.10
(48/48)Wonder Full
0.00%± 1.07
(48/48)Legal Research Bench *
Inkling
0.00%± 3.13
(78/78)Wonder Full
0.00%± 3.47
(78/78)Finance Agent (v2) *
Inkling
0.00%± 0.93
(78/78)Wonder Full
0.00%± 0.21
(78/78)Tax Agent Bench *
Inkling
0.00%± 2.42
(69/69)Wonder Full
0.00%± 3.57
(69/69)MedCode *
Inkling
0.00%± 2.23
(107/107)Wonder Full
0.00%± 2.18
(107/107)Terminal-Bench Science
Inkling
N/AWonder Full
0.00%± 5.82
(41/41)Code Migration *
Inkling
0.00%± 3.40
(77/77)Wonder Full
0.00%± 4.42
(77/77)Terminal-Bench 4.0
Inkling
0.00%± 0.51
(48/48)Wonder Full
0.00%± 3.31
(48/48)Vibe Code Bench v1.1 *
Inkling
0.00%± 3.66
(112/112)Wonder Full
0.00%± 1.93
(112/112)Overall performance
Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, and law
•2026-10-13
Comparison by Industry
Model performance on different sections of the economy.
Legal
37.80%
vs.54.15%
Finance
47.91%
vs.57.99%
Healthcare
63.30%
vs.69.63%
Math
0.00%
vs.94.00%
Science
N/A
vs.39.01%
Academic
83.97%
vs.N/A
Education
36.55%
vs.N/A
Coding
27.00%
vs.52.39%
Cyber
33.39%
vs.42.73%
Social Mobility
58.46%
vs.73.75%
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
$1.463
$8.559
Cost / TestVals Index
$1.463
vs.$8.559
Input Cost/ 1M Tokens
$1.00
vs.$4.00
Input Cache Read/ 1M Tokens
$0.17
vs.$0.20
Output Cost/ 1M Tokens
$4.05
vs.$20.00
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | Thinking Machines | Meta |
| Latency | 1206.78s | 3395.76s |
| Cost (In/Out) | $1 / $4.05 | $4 / $20 |
| Context Window | 256k | 1M |
| Max Output Token | 256k | 131k |
| Input Modality |