FORTIS - Skill-Grounded Tool Selection: leaderboard
Metric: Exact-match rate (%) with the minimum-privilege tool set on FORTIS Task 2 (skill-grounded tool selection, 1,543 queries: the model gets the assigned skill document and the full tool inventory and must pick the minimum-privilege feasible tool set), temperature 0; higher is better. Source: arxiv.org. Saturation forecast: Around 2030. 10 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.7 | 26.1 |
| 2 | Qwen 3.6 Max | 25.9 |
| 3 | Kimi K2.6 | 23.3 |
| 4 | Gemini 3.1 Pro (Preview) | 22.7 |
| 5 | Claude Sonnet 4.6 | 22.4 |
| 6 | DeepSeek V4 Flash | 20.7 |
| 7 | GPT-5.5 | 20.4 |
| 8 | GPT-5.4 Mini | 19.7 |
| 9 | Gemini 3 Flash | 16.9 |
| 10 | GPT-5.4 | 15.2 |
Interactive version: theaggregate.ai/benchmark?slug=fortis-skill-grounded-tool-selection · How It Works · Data refreshed daily, snapshot 2026-10-07.