However, while popular, the system's suitability for assessing entities with constant skill levels, such as LLMs, remains relatively unexplored. We study two fundamental axioms that evaluation methods should adhere to: reliability and transitivity .

However, while popular, the system's suitability for assessing entities with constant skill levels, such as LLMs, remains relatively unexplored. We study two fundamental axioms that evaluation methods should adhere to: reliability and transitivity .

In arena-style evaluation of large language models (LLMs), two LLMs respond to a user query, and the user chooses the winning response or deems the "battle" a draw, resulting in an adjustment to the ratings of both models. The prevailing approach for modeling these rating dynamics is to view battles as two-player game matches, as in chess, and apply the Elo rating system and its derivatives. In this paper, we critically examine this paradigm. Specifically, we question whether a draw genuinely means that the two models are equal and hence whether their ratings should be equalized. Instead, we conjecture that draws are more indicative of query difficulty: if the query is too easy, then both models are more likely to succeed equally. On three real-world arena datasets, we show that ignoring rating updates for draws yields a 1-3% relative increase in battle outcome prediction accuracy (which includes draws) for all four rating systems studied. Further analyses suggest that draws occur more for queries rated as very easy and those as highly objective, with risk ratios of 1.37 and 1.35, respectively. We recommend future rating systems to reconsider existing draw semantics and to account for query properties in rating updates.

Knowledge of accurate relative skills in any competitive system is essential, but foundational approaches such as ELO discard extremely relevant performance data by concentrating exclusively on binary outcomes. While margin of victory (MOV) extensions exist, they often lack a definitive method for incorporating this information. We introduce Margin of Victory Differential Analysis (MOVDA), a framework that enhances traditional rating systems by using the deviation between the true MOV and a $\textit{modeled expectation}$. MOVDA learns a domain-specific, non-linear function (a scaled hyperbolic tangent that captures saturation effects and home advantage) to predict expected MOV based on rating differentials. Crucially, the $\textit{difference}$ between the true and expected MOV provides a subtle and weighted signal for rating updates, highlighting informative deviations in all levels of contests. Extensive experiments on professional NBA basketball data (from 2013 to 2023, with 13,619 games) show that MOVDA significantly outperforms standard ELO and Bayesian baselines. MOVDA reduces Brier score prediction error by $1.54\%$ compared to TrueSkill, increases outcome accuracy by $0.58\%$, and most importantly accelerates rating convergence by $13.5\%$, while maintaining the computational efficiency of the original ELO updates. MOVDA offers a theoretically motivated, empirically superior, and computationally lean approach to integrating performance magnitude into skill rating for competitive environments like the NBA.

As the field progresses toward Artificial General Intelligence (AGI), there is a pressing need for more comprehensive and insightful evaluation frameworks that go beyond aggregate performance metrics. This paper introduces a unified rating system that jointly models the difficulty of individual test cases and the competency of AI models (or humans) across vision, language, and action domains. Unlike existing metrics that focus solely on models, our approach allows for fine-grained, difficulty-aware evaluations through competitive interactions between models and tasks, capturing both the long-tail distribution of real-world challenges and the competency gap between current models and full task mastery. We validate the generalizability and robustness of our system through extensive experiments on multiple established datasets and models across distinct AGI domains. The resulting rating distributions offer novel perspectives and interpretable insights into task difficulty, model progression, and the outstanding challenges that remain on the path to achieving full AGI task mastery.

Benchmarking is a fundamental practice in machine learning (ML) for comparing the performance of classification algorithms. However, traditional evaluation methods often overlook a critical aspect: the joint consideration of dataset complexity and an algorithm's ability to generalize. Without this dual perspective, assessments may favor models that perform well on easy instances while failing to capture their true robustness. To address this limitation, this study introduces a novel evaluation methodology that combines Item Response Theory (IRT) with the Glicko-2 rating system, originally developed to measure player strength in competitive games. IRT assesses classifier ability based on performance over difficult instances, while Glicko-2 updates performance metrics - such as rating, deviation, and volatility - via simulated tournaments between classifiers. This combined approach provides a fairer and more nuanced measure of algorithm capability. A case study using the OpenML-CC18 benchmark showed that only 15% of the datasets are truly challenging and that a reduced subset with 50% of the original datasets offers comparable evaluation power. Among the algorithms tested, Random Forest achieved the highest ability score. The results highlight the importance of improving benchmark design by focusing on dataset quality and adopting evaluation strategies that reflect both difficulty and classifier proficiency.

Theoretical work on sequential choice and large-scale experiments in online ranking and voting systems has demonstrated that social influence can have a drastic impact on social and technological systems. Yet, the effect of social influence on online rating systems remains understudied and the few existing contributions suggest that online ratings would self-correct given enough users. Here, we propose a new framework for studying the effect of social influence on online ratings. We start from the assumption that people are influenced linearly by the observed average rating, but postulate that their propensity to be influenced varies. When the weight people assign to the observed average depends only on their own latent rating, the resulting system is linear, but the long-term rating may substantially deviate from the true mean rating. When the weight people put on the observed average depends on both their own latent rating and the observed average rating, the resulting system is non-linear, and may support multiple equilibria, suggesting that ratings might be path-dependent and deviations dramatic. Our results highlight potential limitations in crowdsourced information aggregation and can inform the design of more robust online rating systems.

Elo rating, widely used for skill assessment across diverse domains ranging from competitive games to large language models, is often understood as an incremental update algorithm for estimating a stationary Bradley-Terry (BT) model. However, our empirical analysis of practical matching datasets reveals two surprising findings: (1) Most games deviate significantly from the assumptions of the BT model and stationarity, raising questions on the reliability of Elo. (2) Despite these deviations, Elo frequently outperforms more complex rating systems, such as mElo and pairwise models, which are specifically designed to account for non-BT components in the data, particularly in terms of win rate prediction. This paper explains this unexpected phenomenon through three key perspectives: (a) We reinterpret Elo as an instance of online gradient descent, which provides no-regret guarantees even in misspecified and non-stationary settings. (b) Through extensive synthetic experiments on data generated from transitive but non-BT models, such as strongly or weakly stochastic transitive models, we show that the ''sparsity'' of practical matching data is a critical factor behind Elo's superior performance in prediction compared to more complex rating systems. (c) We observe a strong correlation between Elo's predictive accuracy and its ranking performance, further supporting its effectiveness in ranking.

In competitive games, strength ratings like Elo are widely used to quantify player skill and support matchmaking by accounting for skill disparities better than simple win rate statistics. However, scalar ratings cannot handle complex intransitive relationships, such as counter strategies seen in Rock-Paper-Scissors. To address this, recent work introduced Neural Rating Table and Neural Counter Table, which combine scalar ratings with discrete counter categories to model intransitivity. While effective, these methods rely on neural network training and cannot perform real-time updates. In this paper, we propose an online update algorithm that extends Elo principles to incorporate real-time learning of counter categories. Our method dynamically adjusts both ratings and counter relationships after each match, preserving the explainability of scalar ratings while addressing intransitivity. Experiments on zero-sum competitive games demonstrate its practicality, particularly in scenarios without complex team compositions.

To take the esports scene to the next level, we introduce PandaSkill, a framework for assessing player performance and skill rating. Traditional rating systems like Elo and TrueSkill often overlook individual contributions and face challenges in professional esports due to limited game data and fragmented competitive scenes. PandaSkill leverages machine learning to estimate in-game player performance from individual player statistics. Each in-game role is modeled independently, ensuring a fair comparison between them. Then, using these performance scores, PandaSkill updates the player skill ratings using the Bayesian framework OpenSkill in a free-for-all setting. In this setting, skill ratings are updated solely based on performance scores rather than game outcomes, hightlighting individual contributions. To address the challenge of isolated rating pools that hinder cross-regional comparisons, PandaSkill introduces a dual-rating system that combines players' regional ratings with a meta-rating representing each region's overall skill level. Applying PandaSkill to five years of professional League of Legends matches worldwide, we show that our method produces skill ratings that better predict game outcomes and align more closely with expert opinions compared to existing methods.