FORTIS - Skill-Grounded Tool Selection Fail Rate: leaderboard
Share (%) of 1,543 skill-grounded tool-selection queries on which a model selects tools beyond the minimum-privilege set or takes no action. FORTIS (2026) builds 20-skill libraries with hidden privilege levels over email, e-commerce and filesystem domains. Lower is better.
Metric: Fail rate (%), the share of over-privileged or no-action outcomes, 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; lower is better. Source: arxiv.org. Saturation forecast: Not forecast. 10 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3.6 Max | 45.2 | #193 |
| 2 | Claude Opus 4.7 | 47.4 | #85 |
| 3 | Gemini 3.1 Pro (Preview) | 49.2 | #99 |
| 4 | DeepSeek V4 Flash | 53 | #267 |
| 5 | Kimi K2.6 | 53.7 | #192 |
| 6 | Claude Sonnet 4.6 | 56.8 | #173 |
| 7 | GPT-5.4 Mini | 59.3 | #406 |
| 8 | Gemini 3 Flash | 61.2 | #175 |
| 9 | GPT-5.5 | 62.5 | #54 |
| 10 | GPT-5.4 | 66.6 | #135 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=fortis-skill-grounded-tool-selection-fail-rate · How It Works · Data refreshed daily, snapshot 2026-11-21.