HELM Robo-Reward-Bench - Robo Reward Bench Progress Prediction: leaderboard
Metric: Absolute error. Source: crfm.stanford.edu. 18 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro (Preview 05-06) | 18.15 |
| 2 | GPT-4.1 (2025-04-14) | 20.46 |
| 3 | O1 (2024-12-17) | 22.2 |
| 4 | GPT-4o (2024-11-20) | 22.89 |
| 5 | GPT-4.5 | 24.67 |
| 6 | Gemini 2.5 Flash (Preview 04-17) | 25.1 |
| 7 | Gemini 2.5 Flash (Preview 05-20) | 26.56 |
| 8 | Gemini 2.0 Flash Lite | 27.54 |
| 9 | Gemini 2.0 Flash | 27.63 |
| 10 | GPT-4.1 Mini | 36.17 |
Interactive version: theaggregate.ai/benchmark?slug=helm-robo-reward-bench-robo-reward-bench-progress-prediction · How It Works · Data refreshed daily, snapshot 2026-09-08.