Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

FUTUREX

Benchmarks

Task NameDataset NameSOTA ResultTrend
ForecastingFutureX
Brier Score0.187
16
Web-retrieval Task CompletionFutureX
Pass@149.5
14
Agent EvaluationFutureX May W2, 56 events
Rank5
6
Future PredictionFUTUREX March 2026 Week 3 slice
L1 Score71.43
6
Agent EvaluationFutureX 48 events May W1
Rank1
3
Agent EvaluationFutureX Apr. W4 48 events
Rank1
3
Agent EvaluationFutureX 56 events Apr. W3
Rank2
3
Showing 7 of 7 rows