Personalized RewardBench - Society and Culture: leaderboard
Personalized preference judgment on the 1,074 Society and Culture test pairs of Personalized RewardBench (2026): for LaMP-QA queries, the chosen response follows the user-specific rubric aspects while the rejected one, of similar general quality, does not. Pairwise accuracy in percent (scalar models must score the chosen response higher, generative models pick it); higher is better.
Metric: Pairwise accuracy (%) on the 1,074 Society and Culture test pairs of Personalized RewardBench, where the chosen response follows the user-specific rubric aspects and the rejected one avoids them while keeping general quality (human-validated); scalar models must score the chosen response strictly higher, generative models pick one of the two in shuffled order; no user profile in the input; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 17 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Flash | 75.51 | #175 |
| 2 | InternLM2-7B-Reward | 74.95 | |
| 3 | Claude Sonnet 4.6 | 73.56 | #173 |
| 4 | Skywork-Reward-V2-Llama-3.1-8B | 71.88 | |
| 5 | R3-Qwen3-14B-14k | 71.88 | |
| 6 | RM-R1-Qwen2.5-Instruct-14B | 69.65 | |
| 7 | Skywork-Reward-V2-Llama-3.2-3B | 69.18 | |
| 8 | R3-Qwen3-8B-14k | 68.9 | |
| 9 | mR3-Qwen3-4B | 68.53 | |
| 10 | R3-Qwen3-4B-14k | 68.16 | |
| 11 | Skywork-Reward-V2-Llama-3.2-1B | 67.88 | |
| 12 | RM-R1-Qwen2.5-Instruct-7B | 67.69 | |
| 13 | InternLM2-20B-Reward | 67.13 | |
| 14 | GPT-5.1 | 66.76 | #240 |
| 15 | mR3-Qwen3-8B | 66.29 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=personalized-rewardbench-society-and-culture · How It Works · Data refreshed daily, snapshot 2026-11-21.