Agent2 RL-Bench - DeepSearchQA: leaderboard
Metric: DeepSearchQA accuracy (%) on 200 held-out questions with a search tool and an LLM judge 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 2029. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.6 | 23 |
| 2 | GPT-5.4 | 21 |
| 3 | Claude Sonnet 4.5 | 18.5 |
| 4 | GPT-4o | 17 |
| 5 | Gemini 2.5 Flash | 13 |
| 6 | GPT-5.2 | 12 |
Interactive version: theaggregate.ai/benchmark?slug=agent2-rl-bench-deepsearchqa · How It Works · Data refreshed daily, snapshot 2026-10-07.