Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

Text-based Game Playing research benchmarks · SOTA2 Research

Text-based Game Playing

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

J-TTL Jericho (test-time learning)

95Detective Score

20

Apr 20, 2026

Jericho Zork3 (test)

3.1Avg Score

7

Feb 26, 2026

Jericho Zork1 (test)

53Average Score

7

Feb 26, 2026

Jericho Library (test)

25.9Average Score

7

Feb 26, 2026

73Zork1 Score

6

May 21, 2026

TW-Cooking 1000 (test)

REUSERL-SegCost (no buffer)

83.5Pass@1

5

Jun 1, 2026

TWC out-of-distribution (Hard)

—

—Primary metric

0

Feb 26, 2026

TWC out-of-distribution Medium

—

—Primary metric

0

Feb 26, 2026

TWC out-of-distribution (Easy)

—

—Primary metric

0

Feb 26, 2026

Popular datasets

Jericho TWC J-TTL TW-Cooking

Follow for updates

Join SOTA2 Contact