OdysseyBench: leaderboard
Metric: Overall (Old) (self-reported). Source: benchmarklist.com. 10 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | O3 | 56.19 |
| 2 | GPT-5 | 54 |
| 3 | GPT-5 Chat | 40.33 |
| 4 | DeepSeek R1 | 39.33 |
| 5 | GPT-4.1 | 35.67 |
| 6 | GPT-4o | 33.67 |
| 7 | Qwen 3 32B | 27 |
| 8 | O3 Mini | 23.75 |
| 9 | GPT-4o Mini | 19 |
Interactive version: theaggregate.ai/benchmark?slug=odysseybench · How It Works · Data refreshed daily, snapshot 2026-09-05.