FoodTruckBench: leaderboard
Source-selected end net worth in dollars after a completed 30-day-or-bankruptcy food-truck simulation. Native cents and selected run IDs are preserved. Declared repetition counts vary; the separately disclosed JSON sanitization condition is kept on its own board.
Metric: Source-selected End Net Worth ($). Source: foodtruckbench.com. Saturation forecast: Around October 2027. 57 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 5 | 75263.63 | #12 |
| 2 | Claude Fable 5.1 | 62732.17 | #9 |
| 3 | GPT-5.5 (2026-04-23) | 61408.09 | #22 |
| 4 | Grok 4.6 | 59537.27 | #26 |
| 5 | GPT-6 Astra | 57760.9 | #6 |
| 6 | GPT-5.6 Sol | 53229.1 | #19 |
| 7 | DeepSeek V4.1 Flash | 50178.66 | #36 |
| 8 | Claude Opus 4.6 | 49519.37 | #63 |
| 9 | MiMo-V2.6-Pro | 49373.25 | #42 |
| 10 | Grok 4.7 | 42560.74 | #25 |
| 11 | Muse Spark 1.2 | 41904.3 | #62 |
| 12 | Hy4 preview | 39037.43 | #38 |
| 13 | DeepSeek V4 Pro (0813) | 37349.92 | #53 |
| 14 | Grok 4.5 | 34585.92 | #48 |
| 15 | GPT-5.6 Luna | 32931.72 | #68 |
No result here: #3 Claude Opus 5.5, #7 GPT-6.1 Sol, #8 Gemini 4 Argon.
Interactive version: theaggregate.ai/benchmark?slug=foodtruckbench · How It Works · Data refreshed daily, snapshot 2026-10-20.