Enterprises have to know if the fashions that energy their purposes and brokers work in real-life eventualities. Such a analysis can generally be advanced as a result of it’s onerous to foretell particular eventualities. A revamped model of the RewardBench benchmark seems to be to present organizations a greater concept of a mannequin’s real-life efficiency.
The Allen Institute of AI (Ai2) launched RewardBench 2, an up to date model of its reward mannequin benchmark, RewardBench, which they declare gives a extra holistic view of mannequin efficiency and assesses how fashions align with an enterprise’s objectives and requirements.
Ai2 constructed RewardBench with classification duties that measure correlations by means of inference-time compute and downstream coaching. RewardBench primarily offers with reward fashions (RM), which might act as judges and consider LLM outputs. RMs assign a rating or a “reward” that guides reinforcement studying with human suggestions (RHLF).
RewardBench 2 is right here! We took a very long time to study from our first reward mannequin analysis device to make one that’s considerably more durable and extra correlated with each downstream RLHF and inference-time scaling. pic.twitter.com/NGetvNrOQV
— Ai2 (@allen_ai) June 2, 2025
Nathan Lambert, a senior analysis scientist at Ai2, instructed VentureBeat that the primary RewardBench labored as supposed when it was launched. Nonetheless, the mannequin surroundings quickly advanced, and so ought to its benchmarks.
“As reward models became more advanced and use cases more nuanced, we quickly recognized with the community that the first version didn’t fully capture the complexity of real-world human preferences,” he stated.
Lambert added that with RewardBench 2, “we set out to improve both the breadth and depth of evaluation—incorporating more diverse, challenging prompts and refining the methodology to reflect better how humans actually judge AI outputs in practice.” He stated the second model makes use of unseen human prompts, has a tougher scoring setup and new domains.
Utilizing evaluations for fashions that consider
Whereas reward fashions check how properly fashions work, it’s additionally vital that RMs align with firm values; in any other case, the fine-tuning and reinforcement studying course of can reinforce dangerous habits, similar to hallucinations, cut back generalization, and rating dangerous responses too excessive.
RewardBench 2 covers six completely different domains: factuality, exact instruction following, math, security, focus and ties.
“Enterprises should use RewardBench 2 in two different ways depending on their application. If they’re performing RLHF themselves, they should adopt the best practices and datasets from leading models in their own pipelines because reward models need on-policy training recipes (i.e. reward models that mirror the model they’re trying to train with RL). For inference time scaling or data filtering, RewardBench 2 has shown that they can select the best model for their domain and see correlated performance,” Lambert stated.
Lambert famous that benchmarks like RewardBench provide customers a method to consider the fashions they’re selecting primarily based on the “dimensions that matter most to them, rather than relying on a narrow one-size-fits-all score.” He stated the concept of efficiency, which many analysis strategies declare to evaluate, could be very subjective as a result of a very good response from a mannequin extremely is determined by the context and objectives of the person. On the identical time, human preferences get very nuanced.
Ai 2 launched the primary model of RewardBench in March 2024. On the time, the corporate stated it was the primary benchmark and leaderboard for reward fashions. Since then, a number of strategies for benchmarking and enhancing RM have emerged. Researchers at Meta’s FAIR got here out with reWordBench. DeepSeek launched a brand new method known as Self-Principled Critique Tuning for smarter and scalable RM.
How fashions carried out
Since RewardBench 2 is an up to date model of RewardBench, Ai2 examined each current and newly educated fashions to see in the event that they proceed to rank excessive. These included quite a lot of fashions, similar to variations of Gemini, Claude, GPT-4.1, and Llama-3.1, together with datasets and fashions like Qwen, Skywork, and its personal Tulu.
The corporate discovered that bigger reward fashions carry out finest on the benchmark as a result of their base fashions are stronger. General, the strongest-performing fashions are variants of Llama-3.1 Instruct. When it comes to focus and security, Skywork knowledge “is particularly helpful,” and Tulu did properly on factuality.
Ai2 stated that whereas they consider RewardBench 2 “is a step forward in broad, multi-domain accuracy-based evaluation” for reward fashions, they cautioned that mannequin analysis must be primarily used as a information to choose fashions that work finest with an enterprise’s wants.
Day by day insights on enterprise use circumstances with VB Day by day
If you wish to impress your boss, VB Day by day has you coated. We provide the inside scoop on what firms are doing with generative AI, from regulatory shifts to sensible deployments, so you may share insights for optimum ROI.
An error occured.