MemoryArena - Group Travel Planning Soft Progress Score: leaderboard
Metric: Soft progress score (%) on Group Travel Planning (270 tasks of five to nine sessions): each subtask earns the share of its constraints satisfied, averaged within and then over tasks (task success and hard progress are near zero for every system); the model is the task agent and keeps its full interaction history in context (no external memory); printed as fractions and shown times 100; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 5 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Sonnet 4.6 | 89 | #85 |
| 2 | Gemini 3 Flash | 62 | #93 |
| 3 | Claude Sonnet 4.5 | 44 | #138 |
| 4 | GPT-4.1 Mini | 19 | #346 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=memoryarena-group-travel-planning-soft-progress-score · How It Works · Data refreshed daily, snapshot 2026-10-11.