PilotBench - Instruction Following: leaderboard
PilotBench (2026) evaluates LLMs as general-aviation flight predictors: from structured historical waypoints of real trajectories across nine flight phases, a model predicts the next trajectory and attitude state in a fixed output schema at temperature 0. This board is the instruction-following score in percent, combining field completeness, field validity and format compliance of the predicted schema; higher is better.
Metric: Instruction-following score (%): 0.5 x field completeness plus 0.3 x field validity plus 0.2 x format compliance of the predicted schema, on PilotBench (one-step trajectory and attitude prediction from 34-channel telemetry of 708 general-aviation trajectories in nine flight phases, fixed output schema, temperature 0); higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 19 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3 32B | 97.43 | #972 |
| 2 | Qwen 2.5 14B Instruct | 96.65 | #1775 |
| 3 | Qwen 2.5 72B Instruct | 96.64 | #1117 |
| 4 | glm-4-9B | 96.45 | #2738 |
| 5 | DeepSeek V3 | 96 | #729 |
| 6 | GPT-4o Mini | 95.74 | #1667 |
| 7 | Qwen 2.5 7B Instruct | 95.32 | #2723 |
| 8 | Qwen 2.5 VL 72B Instruct | 94.89 | #841 |
| 9 | Qwen 2.5 32B Instruct | 94.66 | #1247 |
| 10 | DeepSeek-R1-Distill-Qwen-7B | 94.42 | #8055 |
| 11 | Qwen 3 14B | 94.09 | #1269 |
| 12 | Doubao-1.5-Pro-32k | 93.5 | #694 |
| 13 | O3 Mini | 93.05 | #546 |
| 14 | DeepSeek R1 Distill Qwen 32B | 91.07 | #1834 |
| 15 | QwQ-32B | 83.95 | #907 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=pilotbench-instruction-following · How It Works · Data refreshed daily, snapshot 2026-11-21.