ResearchGym - Improving Replay Buffers: leaderboard

Metric: Best-of-3 score normalised to the task's reference (SOTA) result, SOTA = 100. Source: anikethh.github.io. Saturation forecast: Rough model projection: around 2026. 3 models tracked.

Top models

#ModelScore
1gpt-5.2-codex (Codex, xhigh)49.7
2RG-Agent + gpt-5 (high)34.3
3claude-opus-4.5 (Claude Code)21.7

Interactive version: theaggregate.ai/benchmark?slug=researchgym-improving-replay-buffers · How It Works · Data refreshed daily, snapshot 2026-09-26.