Native Robot Reasoning - LIBERO - Object: leaderboard
Appendix Table 2; native API/vision-language control loop; exact effort preserved. Excludes cited pi0.5 and trained unreleased Ours. No synthetic timeout correction. Metric: Success rate (%). Source: https://arxiv.org/html/2611.18562v1
Metric: Success rate (%). Source: arxiv.org. Saturation forecast: Around February 2027. 3 models tracked. Updated 17 Nov 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | GPT-6.1 Sol | Max | 83.4 | #12 |
| 2 | GPT-6 Astra | Max | 82.2 | #8 |
| 3 | Qwen 3.8 27B | xHigh | 1.8 | #219 |
No result here: #1 Claude Fable 5.2, #2 GPT-6.2 Astra, #3 Gemini 4 Carbon.
Interactive version: theaggregate.ai/benchmark?slug=native-robot-reasoning-libero-object · How It Works · Data refreshed daily, snapshot 2026-11-17.