LLM2014 Logic 2026-05: leaderboard
Metric: Median Score. Source: raw.githubusercontent.com. 43 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 (xHigh) | 80.47 |
| 2 | Claude Opus 4.6 (High) | 76.48 |
| 3 | Gemini 3.5 Flash (High) | 73.93 |
| 4 | Claude Opus 4.8 (xHigh) | 68.32 |
| 5 | Gemini 3.1 Pro (Preview) (High) | 67.91 |
| 6 | DeepSeek V4 Pro (Max) | 64.82 |
| 7 | Seed 2.0 Pro (High) | 57.4 |
| 8 | GLM-5.1 | 55.59 |
| 9 | DeepSeek V4 Flash (Max) | 50.97 |
| 10 | Kimi K2.6 | 47.81 |
| 11 | Hy3-preview | 47.01 |
| 12 | Qwen 3.6 Plus | 44.99 |
| 13 | Claude Opus 4.6 | 43.29 |
| 14 | GPT-5.4 Mini (High) | 40.59 |
| 15 | Claude Sonnet 4.5 | 39.93 |
Interactive version: theaggregate.ai/benchmark?slug=llm2014-logic-2026-05 · How It Works · Data refreshed daily, snapshot 2026-09-05.