PulseAugur
EN
LIVE 10:25:17

New KellyBench benchmark reveals AI models fail sports betting markets

By PulseAugur Editorial · [2 sources] ·

Researchers have introduced KellyBench, a new benchmark designed to evaluate the long-horizon sequential decision-making capabilities of language models in dynamic environments. The benchmark simulates sports betting markets, specifically the English Premier League, challenging agents to maximize bankroll growth using historical data and public odds. Initial evaluations showed that even advanced models struggled, with the best performer losing 8% on average and many experiencing financial ruin, indicating a significant gap compared to human expert strategies. AI

IMPACT Highlights limitations of current frontier models in complex, dynamic environments, suggesting a need for improved adaptive strategies.

RANK_REASON The cluster describes a new academic benchmark for evaluating AI models.

Read on arXiv cs.AI →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

New KellyBench benchmark reveals AI models fail sports betting markets

How we ranked this

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
The cluster describes a new academic benchmark for evaluating AI models.
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
paper, other
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
122 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

Full methodology in our editorial standards.

COVERAGE [2]

  1. arXiv cs.AI TIER_1 English(EN) · Thomas Grady, Kip Parker, Iliyan Zarov, Henry Course, Chengxi Taylor, Ross Taylor ·

    KellyBench: A Benchmark for Long-Horizon Sequential Decision Making

    arXiv:2604.27865v1 Announce Type: new Abstract: Language models are saturating benchmarks for procedural tasks with narrow objectives. But they are increasingly being deployed in long-horizon, non-stationary environments with open-ended goals. In this paper we introduce KellyBenc…

  2. arXiv cs.AI TIER_1 English(EN) · Ross Taylor ·

    KellyBench: A Benchmark for Long-Horizon Sequential Decision Making

    Language models are saturating benchmarks for procedural tasks with narrow objectives. But they are increasingly being deployed in long-horizon, non-stationary environments with open-ended goals. In this paper we introduce KellyBench, an environment for evaluating sequential deci…

RELATED ENTITIES

RELATED TOPICS