Native Robot Reasoning - LIBERO - Long: 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

#ModelSettingScoreOverall rank
1GPT-6 AstraMax77.4#8
2GPT-6.1 SolMax65.8#12
3Qwen 3.8 27BxHigh0.4#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-long · How It Works · Data refreshed daily, snapshot 2026-11-17.