FORTIS — leaderboard
Metric: Task 1 EM (self-reported). Source: benchmarklist.com. 10 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.7 | 54.8 |
| 2 | Claude Sonnet 4.6 | 49.5 |
| 3 | Gemini 3.1 Pro (Preview) | 47.7 |
| 4 | Gemini 3 Flash (Preview) | 46.2 |
| 5 | DeepSeek V4 Flash | 46.2 |
| 6 | GPT-5.4 Mini | 43.5 |
| 7 | GPT-5.4 | 42.2 |
| 8 | GPT-5.5 | 41.2 |
Interactive version: theaggregate.ai/benchmark?slug=fortis · How the rankings work · Data refreshed daily, snapshot 2026-07-22.