Who leads the RLBench benchmark?

RVT-2 currently leads RLBench with a score of 81.4 on Success Rate (%).

What is the state-of-the-art score on RLBench?

The state-of-the-art result on RLBench is 81.4 (Success Rate (%)), achieved by RVT-2 as of 2026.

How many models are tracked on RLBench?

Codesota tracks 3 models on RLBench.

When was the RLBench leaderboard last updated?

The RLBench leaderboard on Codesota includes results through 2026.

Codesota · Benchmark · RLBenchHome/Leaderboards/RLBench

Imperial College London

RLBench.

Name: RLBench Benchmark Results
Creator: Imperial College London
Published: 2026-01-01
License: https://creativecommons.org/licenses/by/4.0/

Large-scale robot learning benchmark with 100 diverse manipulation tasks in simulation. Standard multi-task benchmark for language-conditioned robotic manipulation. Evaluated on 18 tasks with 100 demonstrations.

Paper ↗Leaderboard ↓

§ 01 · Leaderboard

Results by metric.

Only 3 models on this benchmark

Help build the community leaderboard — submit your model results.

Found a wrong score or missing run?

Use row edits to send a sourced correction into moderation.

Add / edit result ↗Report issue ↗

Success Rate (%)

Average task success rate across 18 RLBench manipulation tasks with 100 demonstrations each.

Higher is better

Trust tiers for Success Rate (%)verifiedpapervendorcommunityunverified

Muted rows were not state of the art when published — an earlier or same-year result already scored better.

Rank	Model	Trust	Score	Year	Links	Fix
01	RVT-2 Fetched from CodeSOTA API on 2026-04-20	verified	81.4	2026	Source ↗	Looks wrong?
02	RVT Fetched from CodeSOTA API on 2026-04-20	verified	62.9	2026	Source ↗	Looks wrong?
03	PerAct Fetched from CodeSOTA API on 2026-04-20	verified	43.4	2026	Source ↗	Looks wrong?

§ 04 · Submit a result

Add to the leaderboard.

Submit a Result

← Back to Leaderboards