Harbor-Index 1.0 (Terminus-2): leaderboard
Metric: Pass rate (%; 82 tasks, one run each). Source: arxiv.org. Saturation forecast: Around February 2028. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 | 19.5 |
| 2 | Claude Opus 4.8 | 15.9 |
| 3 | Gemini 3.1 Pro (Preview) | 11 |
| 4 | GLM-5.2 | 9.8 |
| 5 | Kimi K2.6 | 8.5 |
| 6 | MiniMax-M3 | 6.1 |
| 7 | Qwen 3.7 Max | 4.9 |
| 8 | DeepSeek V4 Pro | 3.7 |
| 9 | MiMo-V2.5-Pro | 2.4 |
Interactive version: theaggregate.ai/benchmark?slug=harbor-index-1-0-terminus-2 · How It Works · Data refreshed daily, snapshot 2026-09-25.