RMGAP - Best-of-4: leaderboard
Metric: Best-of-4 accuracy (%; chosen response scored above all three alternatives, mean of chat, writing, reasoning and safety; scalar reward models score each response, DPO models by their implicit reward against the reference model). Source: arxiv.org. Saturation forecast: Estimated already saturated. 10 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Skywork-Reward-V2-Qwen3-8B | 49.16 |
| 2 | URM-LLaMa-3.1-8B | 45.28 |
| 3 | InternLM2-7B-Reward | 38.23 |
| 4 | Llama-3.1-Tulu-3-8B-DPO | 31.07 |
| 5 | zephyr-7B-beta | 29.91 |
Interactive version: theaggregate.ai/benchmark?slug=rmgap-best-of-4 · How It Works · Data refreshed daily, snapshot 2026-09-26.