Enabling trustworthy AI adoption for transportation.
Developed with transportation professionals, for transportation work.
Overall Leaderboard
| Model | ELO Rating | TB-Safety | TB-Planning Soon | TB-Operations Soon | TB-Aviation Soon |
|---|---|---|---|---|---|
| Claude Sonnet 4.5 | 1294 | - | - | - | - |
| Claude Opus 4.6 | 1231 | - | - | - | - |
| Gemini 3 Flash Preview | 1216 | 41.4% | - | - | - |
| Gemini 1.5 Pro | 1200 | - | - | - | - |
| Gemini 1.5 Pro | 1200 | - | - | - | - |
| GPT-5 mini | 1200 | 47.4% | - | - | - |
| Gemini 3 Pro Preview | 1185 | 44.8% | - | - | - |
| Claude Haiku 4.5 | 1169 | 51.8% | - | - | - |
| GPT-5.2 | 1105 | 53.6% | - | - | - |
| Claude Opus 4.6 | - | 56.3% | - | - | - |
How It Works
Help Improve TransportationBench
Contribute real-world use cases from your transportation work. Get early access to new features and publication credit.
Contribute a Use Case