Metraipolis › archive › dc_7bb87b53675b

AI World Cup 2026: Benchmarking Large Language Models for End-to-End Football Tournament Prediction — arXiv:2608.03416

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.03416
License (as archived): CC0-1.0
Archived: 2026-10-31T12:16:14.801Z
SHA-256 of the archived text: 11c9529e326fa4e9ac3b8f16c6ae306799fd63d3bff89281d7632de73c363982
Stable URL of this page: https://metraipolis.com/documento/dc_7bb87b53675b

How to cite

AI World Cup 2026: Benchmarking Large Language Models for End-to-End Football Tournament Prediction — arXiv:2608.03416 — arXiv (en), https://arxiv.org/abs/2608.03416 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7bb87b53675b (Metraipolis archive dc_7bb87b53675b, sha256 11c9529e326fa4e9ac3b8f16c6ae306799fd63d3bff89281d7632de73c363982)

BibTeX

@misc{dc7bb87b53675b,
  title = {AI World Cup 2026: Benchmarking Large Language Models for End-to-End Football Tournament Prediction — arXiv:2608.03416},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.03416},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7bb87b53675b; sha256 11c9529e326fa4e9ac3b8f16c6ae306799fd63d3bff89281d7632de73c363982},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.03416. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models (LLMs) are now regularly asked to forecast real-world events, but comparisons are often difficult because models receive different information, use different tools, and are evaluated under different rules. This paper reports the completed \emph{AI World Cup} benchmark, in which ten LLM-based assistants made a single pre-tournament forecast of the entire 2026 FIFA World Cup. Every submission used the same tournament snapshot, prompt, JSON schema, and scoring procedure. The forecasts covered group-stage scores, group rankings, the knockout bracket, final placings, confidence values, and short explanations. After all 104 matches had been played, GPT-5.5 Thinking finished first with 744 points, followed by GPT-5.5 with 717, Gemini with 699, and Qwen 3.7 with 687. GPT-5.5 Thinking was also the only model to select Spain, which defeated Argentina 1--0 in the final, as champion. The final ranking was driven mainly by knockout performance: total score was strongly correlated with knockout points ($r=0.986$), but showed little relationship with group-stage match points ($r=0.055$), group-standing points ($r=-0.103$), or their combined pre-knockout score ($r=-0.054$). Match-level accuracy produced a different ordering. Claude Sonnet 4.6 correctly predicted the largest number of group-stage outcomes (63.89\%) but placed sixth overall. Average self-reported confidence was also unrelated to either outcome accuracy ($r=-0.060$) or total score ($r=-0.067$). The results suggest that forecasting a complete tournament tests something different from predicting matches one at a time, while also showing how strongly a bracket-based leaderboard can depend on scoring design. The benchmark materials, raw responses, and scoring code are released to support replication and future extensions.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-05 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.03416 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-31T12:05:52.787Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).