WorldSolver: leaderboard
Metric: Overall score (0-100). Source: arxiv.org. Saturation forecast: Around August 2027. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.6 Sol | 48.7 |
| 2 | Claude Opus 5 | 46.7 |
| 3 | Gemini 3.7 Flash | 29.3 |
| 4 | DeepSeek V4.1 Flash | 24.6 |
| 5 | GLM-5.3 | 23.6 |
| 6 | Qwen 3.8 Max | 22.7 |
| 7 | Kimi K2.7 Code | 17.1 |
Interactive version: theaggregate.ai/benchmark?slug=worldsolver · How It Works · Data refreshed daily, snapshot 2026-10-09.