Agent2 RL-Bench - WebShop: leaderboard

Agentic post-training engineering on Agent^2 RL-Bench (2026): a coding agent driven by the model has 12 hours in an isolated GPU workspace to post-train Qwen3-8B-Base, and the grading server keeps the best checkpoint score of the run. WebShop score of the trained model, from 0 to 100; higher is better.

Metric: WebShop score (0-100) on 100 instructions of the Qwen3-8B-Base model after the coding agent (driver LLM in a CLI scaffold) post-trains it for 12 hours in an isolated GPU workspace, best score the grading server returned over the run, single run; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 6 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Claude Opus 4.678#113
2GPT-5.275#185
3Claude Sonnet 4.568#261
4GPT-5.457#135
5GPT-4o0#751
6Gemini 2.5 Flash0#463

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=agent2-rl-bench-webshop · How It Works · Data refreshed daily, snapshot 2026-11-21.