LLM2014 Logic 2026-10: leaderboard
Metric: Median Score. Source: raw.githubusercontent.com. Saturation forecast: Around August 2028. 39 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-6 (xHigh) | 87.82 |
| 2 | GPT-6.1 Sol (xHigh) | 71.22 |
| 3 | Claude Sonnet 5.5 (xHigh) | 60.69 |
| 4 | Claude Fable 5.1 (xHigh) | 58.69 |
| 5 | GPT-6 Sol (xHigh) | 57.48 |
| 6 | Kimi K3 (Max) | 56.73 |
| 7 | DeepSeek V4.1 Flash (Max) | 56.41 |
| 8 | Grok 4.7 (xHigh) | 55.84 |
| 9 | Gemini 3.8 Flash (High) | 54.54 |
| 10 | GLM-5.3 (Max) | 51.15 |
| 11 | DeepSeek V4 Pro (0813) (Max) | 50.86 |
| 12 | Gemini 3.1 Pro (Preview) (High) | 50.11 |
| 13 | Qwen 3.8 Max (xHigh) | 48.71 |
| 14 | GLM-5.3 Flash (Max) | 48.01 |
| 15 | Muse Spark 1.3 (Max) | 47.26 |
Interactive version: theaggregate.ai/benchmark?slug=llm2014-logic-2026-10 · How It Works · Data refreshed daily, snapshot 2026-10-01.