Personalized RewardBench - Arts and Entertainment: leaderboard
Personalized preference judgment on the 767 Arts and Entertainment 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 767 Arts and Entertainment 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 | 72.36 | #175 |
| 2 | R3-Qwen3-8B-14k | 67.8 | |
| 3 | Claude Sonnet 4.6 | 67.28 | #173 |
| 4 | R3-Qwen3-14B-14k | 66.88 | |
| 5 | Skywork-Reward-V2-Llama-3.1-8B | 66.62 | |
| 6 | InternLM2-7B-Reward | 65.97 | |
| 7 | GPT-5.1 | 65.45 | #240 |
| 8 | RM-R1-Qwen2.5-Instruct-7B | 65.06 | |
| 9 | RM-R1-Qwen2.5-Instruct-14B | 64.8 | |
| 10 | mR3-Qwen3-8B | 64.28 | |
| 11 | InternLM2-20B-Reward | 63.23 | |
| 12 | R3-Qwen3-4B-14k | 62.71 | |
| 13 | Skywork-Reward-V2-Llama-3.2-1B | 62.06 | |
| 14 | mR3-Qwen3-4B | 61.54 | |
| 15 | Skywork-Reward-V2-Llama-3.2-3B | 60.89 |
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-arts-and-entertainment · How It Works · Data refreshed daily, snapshot 2026-11-21.