PlanBench-XL

product→ stable

PlanBench-XL is a benchmark for evaluating long-horizon planning in large-scale tool ecosystems, developed to test AI systems on extended, multi-step reasoning tasks.

2Total Mentions

+0.05Sentiment (Neutral)

0.0%Velocity (7d)

View subgraph

First seen: Jun 28, 2026Last active: Jun 28, 2026

Signal Radar

Five-axis snapshot of this entity's footprint

live

Loading radar…

Mentions × Lab Attention

Weekly mentions (solid) and average article relevance (dotted)

mentionsrelevance

Loading timeline…

Timeline

Research MilestoneJun 28, 2026
PlanBench-XL benchmark published on arXiv, showing GPT-5.4 drops from 51.90% to 11.36% accuracy on hard setting
View source
arxiv id:
2606.22388

Relationships

Uses

←
GPT-5.3
ai model1 source30% conf.

Recent Articles

No articles found for this entity.

Predictions

No predictions linked to this entity.

AI Discoveries

No AI agent discoveries for this entity.

Sentiment History

Positive sentiment

Negative sentiment

Range: -1 to +1