Pith. sign in

REVIEW 8 cited by

ForecastBench: A Dynamic Benchmark of AI Forecasting Capabilities

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2409.19839 v5 pith:LB2FRRFU submitted 2024-09-30 cs.LG cs.AIcs.CL

classification cs.LGcs.AIcs.CL
keywords forecastbenchquestionssystemsbenchmarkforecastingforecastsaccuracycapabilities
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

Forecasts of future events are essential inputs into informed decision-making. Machine learning (ML) systems have the potential to deliver forecasts at scale, but there is no framework for evaluating the accuracy of ML systems on a standardized set of forecasting questions. To address this gap, we introduce ForecastBench: a dynamic benchmark that evaluates the accuracy of ML systems on an automatically generated and regularly updated set of 1,000 forecasting questions. To avoid any possibility of data leakage, ForecastBench is comprised solely of questions about future events that have no known answer at the time of submission. We quantify the capabilities of current ML systems by collecting forecasts from expert (human) forecasters, the general public, and LLMs on a random subset of questions from the benchmark ($N=200$). While LLMs have achieved super-human performance on many benchmarks, they perform less well here: expert forecasters outperform the top-performing LLM ($p$-value $<0.001$). We display system and human scores in a public leaderboard at www.forecastbench.org.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Predicting Empirical AI Research Outcomes with Language Models

    cs.AI 2025-06 conditional novelty 7.0 of 10

    A fine-tuned, retrieval-augmented language model predicts which of two AI research ideas will perform better empirically, beating human experts and frontier models on a new contamination-controlled benchmark.

  2. Adversarial Fast-Moving Real-World Domains as Test Beds for Benchmarking AI Scientist Capabilities

    cs.AI 2026-08 conditional novelty 6.0 of 10

    In two adversarial real-world domains with time-delayed expert ground truth, frontier LLMs over-generate plausible ideas but under-select the specific solutions experts adopted, indicating a filtering and prioritization gap.

  3. WorldCupArena: Fine-Grained Evaluation of Language Models and Deep-Research Agents on Football Forecasting

    cs.AI 2026-07 conditional novelty 6.0 of 10

    A pre-registered benchmark of 13 LLM systems on all 104 World Cup 2026 matches shows fine-grained predictions expose differences that result accuracy hides.

  4. FIFA World Cup 2026 as a Contamination-Free Benchmark for LLM Forecasting Agents: Four Models, a Bookmaker, and 104 Matches

    cs.LG 2026-07 conditional novelty 6.0 of 10

    On 104 World Cup matches, four LLM forecasting agents make identical top picks in 92% of matches, none beats the betting market's Brier score, but their betting ROI spans -18% to +10%.

  5. Beyond Forecasting: The Belief-to-Trade Layer in Prediction-Market Agents

    cs.AI 2026-07 conditional novelty 6.0 of 10

    An explicit selection–sizing–risk trading layer on fixed forecasts yields the only positive ROI and stake-weighted Sharpe among five policies on a Polymarket decision archive.

  6. Bench to the Future: A Pastcasting Benchmark for Forecasting Agents

    cs.CL 2025-06 conditional novelty 6.0 of 10

    Bench to the Future is a pastcasting benchmark: 299 already-resolved forecasting questions, each paired with a frozen corpus of about 20,000 web pages, on which newer LLMs and agentic search score better.

  7. Pitfalls in Evaluating Language Model Forecasters

    cs.LG 2025-05 accept novelty 6.0 of 10

    A systematic critique showing temporal leakage and extrapolation flaws can undermine claims that LLM forecasters match or beat humans.

  8. Question Begets Question: Self-Evolving Curriculum for Reinforcement Fine-Tuning on Competition Mathematics

    cs.LG 2026-08 conditional novelty 5.0 of 10

    A self-evolving curriculum that retrains a language model on variants of problems it can mostly get right lifts AIME pass@1 from 5.6% to 16.5%, beating static augmentation under the same data budget.

Pith tools