Benchmark · PADI
Physical AI Design Index
One question about system design: given the same short requirement for physical AI in a real operation, does Praxis produce a better system design than frontier AI on its own? PADI scores both on fresh tasks across 13 industries in three countries.
RSI Loop 22: blind evaluation on seven unseen tasks, Praxis platform vs frontier AI, checks passed
Tasks where Praxis came out ahead in the blind evaluation
Industries measured across three countries
PADI is the benchmark CodeNinja uses to improve Praxis, one RSI loop (recursive self improvement loop) at a time. Scores are far from saturated: the goal is every check on every task in all 13 industries.
Industries
Checks passed in each industry, all RSI loops to date, for the Praxis platform and frontier AI on its own, on the same tasks. Every industry is measured at least once.
- Agriculture and Earth ObservationRSI Loops 14, 20 · 39 checks
- Aviation ManufacturingRSI Loops 17, 18, 19 · 76 checks
- Defense and IntelligenceRSI Loops 13, 15, 20 · 57 checks
- Discrete Manufacturing and AutomotiveRSI Loops 13, 15, 18 · 76 checks
- Energy and UtilitiesRSI Loops 13, 17, 19, 21 · 153 checks
- Heavy Industry and ConstructionRSI Loop 12 · 56 checks
- Maritime and PortsRSI Loops 12, 16, 19, 20 · 114 checks
- MiningRSI Loops 14, 15, 16, 19, 20 · 129 checks
- Oil and GasRSI Loops 14, 18, 19 · 78 checks
- Rail TransportRSI Loops 14, 15, 16, 19, 21 · 134 checks
- SemiconductorsRSI Loops 18, 20, 21 · 57 checks
- Supply Chain and LogisticsRSI Loops 15, 16, 18 · 57 checks
- Warehousing and IntralogisticsRSI Loops 17, 20, 21 · 96 checks
Trajectory
Every RSI loop on a scale to 100%, so the distance to the goal stays in view.
Loop 22 is a blind evaluation on 7 tasks the platform had never seen. Loops 17 to 21 reused some evaluation tasks, so they are shown for the trend and are not like for like with loop 22.
Results
Every figure is checks passed as a percentage of checks judged, for each arm.
By RSI loop
| RSI Loop | Date | Tasks | Checks per arm | Praxis platform | Frontier AI | Tasks: platform ahead · tied · behind |
|---|---|---|---|---|---|---|
| RSI Loop 12 | 3 Oct 2026 | 6 | 112 | 37.5% | 38.4% | 3 · 0 · 3 |
| RSI Loop 13 | 4 Oct 2026 | 6 | 112 | 29.5% | 32.1% | 3 · 0 · 3 |
| RSI Loop 14 | 5 Oct 2026 | 6 | 111 | 43.2% | 39.6% | 2 · 1 · 3 |
| RSI Loop 15 | 5 Oct 2026 | 6 | 115 | 41.7% | 35.7% | 5 · 0 · 1 |
| RSI Loop 16 | 7 Oct 2026 | 5 | 96 | 36.5% | 26.0% | 5 · 0 · 0 |
| RSI Loop 17 | 8 Oct 2026 | 6 | 117 | 23.9% | 16.2% | 3 · 3 · 0 |
| RSI Loop 18 | 9 Oct 2026 | 6 | 115 | 37.4% | 31.3% | 3 · 1 · 2 |
| RSI Loop 19 | 11 Oct 2026 | 6 | 115 | 41.7% | 27.0% | 6 · 0 · 0 |
| RSI Loop 20 | 11 Oct 2026 | 6 | 115 | 39.1% | 30.4% | 4 · 2 · 0 |
| RSI Loop 21 | 14 Oct 2026 | 6 | 114 | 54.4% | 37.7% | 5 · 1 · 0 |
| All RSI loops | 59 | 1122 | 38.5% | 31.5% | 39 · 8 · 12 | |
| RSI Loop 22, blind | 16 Oct 2026 | 7 | 134 | 48.5% | 28.4% | 7 · 0 · 0 |
By industry
| Industry | RSI Loop | Checks per arm | Praxis platform | Frontier AI |
|---|---|---|---|---|
| Agriculture and Earth Observation | RSI Loop 14 | 20 | 35.0% | 40.0% |
| Agriculture and Earth Observation | RSI Loop 20 | 19 | 57.9% | 31.6% |
| Agriculture and Earth Observation | RSI Loop 22, blind | 18 | 38.9% | 22.2% |
| Aviation Manufacturing | RSI Loop 17 | 40 | 15.0% | 12.5% |
| Aviation Manufacturing | RSI Loop 18 | 18 | 27.8% | 44.4% |
| Aviation Manufacturing | RSI Loop 19 | 18 | 33.3% | 27.8% |
| Aviation Manufacturing | RSI Loop 22, blind | 20 | 50.0% | 30.0% |
| Defense and Intelligence | RSI Loop 13 | 18 | 38.9% | 22.2% |
| Defense and Intelligence | RSI Loop 15 | 19 | 57.9% | 47.4% |
| Defense and Intelligence | RSI Loop 20 | 20 | 30.0% | 30.0% |
| Discrete Manufacturing and Automotive | RSI Loop 13 | 18 | 27.8% | 33.3% |
| Discrete Manufacturing and Automotive | RSI Loop 15 | 19 | 36.8% | 31.6% |
| Discrete Manufacturing and Automotive | RSI Loop 18 | 39 | 53.8% | 35.9% |
| Discrete Manufacturing and Automotive | RSI Loop 22, blind | 19 | 52.6% | 36.8% |
| Energy and Utilities | RSI Loop 13 | 76 | 27.6% | 34.2% |
| Energy and Utilities | RSI Loop 17 | 19 | 31.6% | 15.8% |
| Energy and Utilities | RSI Loop 19 | 19 | 47.4% | 21.1% |
| Energy and Utilities | RSI Loop 21 | 39 | 51.3% | 30.8% |
| Heavy Industry and Construction | RSI Loop 12 | 56 | 44.6% | 46.4% |
| Maritime and Ports | RSI Loop 12 | 56 | 30.4% | 30.4% |
| Maritime and Ports | RSI Loop 16 | 19 | 42.1% | 15.8% |
| Maritime and Ports | RSI Loop 19 | 20 | 30.0% | 20.0% |
| Maritime and Ports | RSI Loop 20 | 19 | 42.1% | 31.6% |
| Maritime and Ports | RSI Loop 22, blind | 19 | 42.1% | 15.8% |
| Mining | RSI Loop 14 | 33 | 66.7% | 54.5% |
| Mining | RSI Loop 15 | 39 | 35.9% | 35.9% |
| Mining | RSI Loop 16 | 19 | 31.6% | 26.3% |
| Mining | RSI Loop 19 | 19 | 42.1% | 26.3% |
| Mining | RSI Loop 20 | 19 | 26.3% | 21.1% |
| Mining | RSI Loop 22, blind | 18 | 66.7% | 27.8% |
| Oil and Gas | RSI Loop 14 | 39 | 28.2% | 25.6% |
| Oil and Gas | RSI Loop 18 | 19 | 26.3% | 21.1% |
| Oil and Gas | RSI Loop 19 | 20 | 40.0% | 35.0% |
| Rail Transport | RSI Loop 14 | 19 | 42.1% | 42.1% |
| Rail Transport | RSI Loop 15 | 20 | 55.0% | 40.0% |
| Rail Transport | RSI Loop 16 | 38 | 34.2% | 28.9% |
| Rail Transport | RSI Loop 19 | 19 | 57.9% | 31.6% |
| Rail Transport | RSI Loop 21 | 38 | 47.4% | 42.1% |
| Semiconductors | RSI Loop 18 | 20 | 35.0% | 20.0% |
| Semiconductors | RSI Loop 20 | 19 | 36.8% | 26.3% |
| Semiconductors | RSI Loop 21 | 18 | 61.1% | 33.3% |
| Semiconductors | RSI Loop 22, blind | 20 | 50.0% | 40.0% |
| Supply Chain and Logistics | RSI Loop 15 | 18 | 27.8% | 22.2% |
| Supply Chain and Logistics | RSI Loop 16 | 20 | 40.0% | 30.0% |
| Supply Chain and Logistics | RSI Loop 18 | 19 | 26.3% | 31.6% |
| Warehousing and Intralogistics | RSI Loop 17 | 58 | 27.6% | 19.0% |
| Warehousing and Intralogistics | RSI Loop 20 | 19 | 42.1% | 42.1% |
| Warehousing and Intralogistics | RSI Loop 21 | 19 | 68.4% | 47.4% |
| Warehousing and Intralogistics | RSI Loop 22, blind | 20 | 40.0% | 25.0% |
By country
| RSI Loop | United States: Praxis vs frontier AI | Saudi Arabia: Praxis vs frontier AI | Pakistan: Praxis vs frontier AI |
|---|---|---|---|
| RSI Loop 12 | 34.2% vs 44.7% | 38.9% vs 44.4% | 39.5% vs 26.3% |
| RSI Loop 13 | 24.3% vs 37.8% | 30.8% vs 30.8% | 33.3% vs 27.8% |
| RSI Loop 14 | 35.0% vs 30.0% | 66.7% vs 54.5% | 31.6% vs 36.8% |
| RSI Loop 15 | 56.4% vs 43.6% | 33.3% vs 28.2% | 35.1% vs 35.1% |
| RSI Loop 16 | 35.9% vs 28.2% | 39.5% vs 23.7% | 31.6% vs 26.3% |
| RSI Loop 17 | 23.1% vs 7.7% | 17.9% vs 17.9% | 30.8% vs 23.1% |
| RSI Loop 18 | 53.8% vs 35.9% | 30.8% vs 25.6% | 27.0% vs 32.4% |
| RSI Loop 19 | 42.1% vs 26.3% | 48.7% vs 33.3% | 36.8% vs 22.8% |
| RSI Loop 20 | 34.2% vs 26.3% | 35.9% vs 35.9% | 47.4% vs 28.9% |
| RSI Loop 21 | 44.7% vs 28.9% | 53.8% vs 43.6% | 64.9% vs 40.5% |
| RSI Loop 22, blind | 52.6% vs 26.3% | 46.9% vs 29.2% |
Coverage
13 of 13 industries measured. 73 tasks in the bank, at least one per industry in each country, because operations differ with the place.
| Industry | United States | Saudi Arabia | Pakistan |
|---|---|---|---|
| Agriculture and Earth Observation | RSI Loop 14 | RSI Loop 22, blind | RSI Loop 20 |
| Aviation Manufacturing | RSI Loop 17Not yet measured | RSI Loop 17RSI Loop 22, blind | RSI Loop 18RSI Loop 19 |
| Defense and Intelligence | RSI Loop 15 | RSI Loop 20 | RSI Loop 13 |
| Discrete Manufacturing and Automotive | RSI Loop 18RSI Loop 18Not yet measured | RSI Loop 15RSI Loop 22, blindNot yet measured | RSI Loop 13 |
| Energy and Utilities | RSI Loop 13RSI Loop 13RSI Loop 21 | RSI Loop 13RSI Loop 13RSI Loop 21 | RSI Loop 17RSI Loop 19 |
| Heavy Industry and Construction | RSI Loop 12 | RSI Loop 12 | RSI Loop 12 |
| Maritime and Ports | RSI Loop 12RSI Loop 20Not yet measured | RSI Loop 12RSI Loop 16RSI Loop 22, blind | RSI Loop 12RSI Loop 19 |
| Mining | RSI Loop 19RSI Loop 20RSI Loop 22, blind | RSI Loop 14RSI Loop 14RSI Loop 15 | RSI Loop 15RSI Loop 16 |
| Oil and Gas | RSI Loop 14 | RSI Loop 19 | RSI Loop 14RSI Loop 18 |
| Rail Transport | RSI Loop 15RSI Loop 16RSI Loop 21 | RSI Loop 16RSI Loop 19RSI Loop 21 | RSI Loop 14 |
| Semiconductors | Not yet measuredNot yet measured | RSI Loop 18RSI Loop 22, blind | RSI Loop 20RSI Loop 21 |
| Supply Chain and Logistics | RSI Loop 16 | RSI Loop 18Not yet measured | RSI Loop 15 |
| Warehousing and Intralogistics | RSI Loop 17RSI Loop 22, blind | RSI Loop 17RSI Loop 20 | RSI Loop 17RSI Loop 21 |
Questions
What is the Physical AI Design Index?
PADI is CodeNinja's benchmark for system design in physical AI. It scores Praxis against frontier AI on its own, on the same short requirements from real kinds of operations such as a mine, a port, a rail line or a substation, across 13 industries in three countries.
How often is PADI updated?
Once per RSI loop, on tasks never run before.
Cadence
Updated each RSI loop. Last published: RSI Loop 22, 16 October 2026. RSI Loop 23 is under way.
Contact
Questions about PADI, or a task from your own operation you would like measured: contact us