Personalized RewardBench - Lifestyle and Personal Development: leaderboard

Personalized preference judgment on the 989 Lifestyle and Personal Development 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 989 Lifestyle and Personal Development 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

#ModelScoreOverall rank
1Gemini 3 Flash75.94#175
2InternLM2-7B-Reward71.69
3GPT-5.170.88#240
4Skywork-Reward-V2-Llama-3.2-1B70.78
5Claude Sonnet 4.670.68#173
6Skywork-Reward-V2-Llama-3.2-3B70.37
7R3-Qwen3-14B-14k70.07
8RM-R1-Qwen2.5-Instruct-7B69.36
9RM-R1-Qwen2.5-Instruct-14B68.96
10R3-Qwen3-8B-14k67.54
11mR3-Qwen3-8B67.54
12InternLM2-20B-Reward67.34
13mR3-Qwen3-4B67.14
14mR3-Qwen3-14B67.14
15Skywork-Reward-V2-Llama-3.1-8B67.04

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-lifestyle-and-personal-development · How It Works · Data refreshed daily, snapshot 2026-11-21.