EPIC-Bench - Feasible Path: leaderboard
EPIC-Bench (2026) is a mask-grounded benchmark of embodied visual perception: 6,661 annotated image, text and mask samples across 23 tasks in target localization, navigation and manipulation, scored by localization, counting, path and feasibility metrics. This board scores planning a point path to the target that stays on traversable ground, on a 0-100 scale; higher is better.
Metric: Navigation path score (0-100) on feasible path planning (a point path from the camera or a marked region to the target that stays on traversable ground), on EPIC-Bench (6,661 human-annotated image, text and mask tuples from 25 public datasets across 23 fine-grained embodied perception tasks; the model outputs bounding boxes, counts, path points or feasibility judgements that are scored against the masks), zero-shot, averaged over six runs for local models and two for API models; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 76 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Gemini 3 Pro | 70.82 | #145 | |
| 2 | Gemini 3.1 Pro (Preview) | 70.32 | #99 | |
| 3 | Claude Sonnet 4.6 | Thinking | 68.46 | #173 |
| 4 | Qwen 3.5 122B A10B | 63.47 | #346 | |
| 5 | Qwen 3.6 Plus | 62.12 | #238 | |
| 6 | Qwen 3.5 35B A3B | 61.17 | #492 | |
| 7 | Qwen 3.5 397B A17B | 60.11 | #264 | |
| 8 | Qwen 3.6 27B | Non-reasoning | 59.15 | #351 |
| 9 | Doubao-Seed-1.6-vision | 58.74 | #361 | |
| 10 | Qwen 3.5 Plus | 57.89 | #242 | |
| 11 | Qwen 3.5 27B | Non-reasoning | 53.5 | #375 |
| 12 | Seed 1.8 | 53.43 | #252 | |
| 13 | Gemini 3 Flash (Preview) | 52.63 | #152 | |
| 14 | Gemini 2.5 Flash | Non-reasoning | 51.98 | #463 |
| 15 | Qwen 3 VL 235B A22B (Thinking) | 51.19 | #459 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=epic-bench-feasible-path · How It Works · Data refreshed daily, snapshot 2026-11-21.