From 0-Order Selection to 2-Order Judgment — leaderboard
Metric: H-Comb (self-reported). Source: benchmarklist.com. 13 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GLM-5 | 38.33 |
| 2 | GPT-5.4 | 31.67 |
| 3 | DeepSeek V4 Pro | 30 |
| 4 | GLM-4.7 | 30 |
| 5 | Claude Opus 4.6 | 26.67 |
| 6 | O3 | 25 |
| 7 | Gemini 3.1 Pro (Preview) | 23.33 |
| 8 | Qwen 3.5 Plus (2026-04-20) | 18.33 |
| 9 | DeepSeek V3.2 | 16.67 |
| 10 | Qwen 3.6 Plus | 5 |
Interactive version: theaggregate.ai/benchmark?slug=from-0-order-selection-to-2-order-judgment · How the rankings work · Data refreshed daily, snapshot 2026-07-22.