WC2026-Agents Benchmark

What is WC2026-Agents?

WC2026-Agents evaluates autonomous LLM forecasting on 104 FIFA World Cup matches using probability forecasts, virtual wagers, and post-match reflections.

Released

2026-07-20

Evaluates

Agents & Tool Use, Finance, cs.LG

Openness

unknown

Importer

Claire Radar

Review status

ai-reviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2607.17765

WC2026-Agents paper and code

• Paper https://arxiv.org/abs/2607.17765
• Code https://github.com/graphuofm/FIFA2026LLM

Which sources cite WC2026-Agents?

• WC2026-Agents

Related Agents & Tool Use, Finance, cs.LG benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• A Large-Scale Dataset and Benchmark
• A3S-Bench
• AdaPlanBench
• Adaptive Adversaries
• ADeptS-Bench
• AdvPlan-Bench
• AeroCopilotBench