LLM2014 Logic 2026-09: leaderboard
Metric: Median Score. Source: raw.githubusercontent.com. 46 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.6 Sol (xHigh) | 70.03 |
| 2 | Claude Opus 5 (xHigh) | 64.42 |
| 3 | Kimi K3 (Max) | 64.32 |
| 4 | Claude Fable 5.1 (xHigh) | 63.47 |
| 5 | Gemini 3.8 Flash (High) | 62.05 |
| 6 | GLM-5.3 (Max) | 59.76 |
| 7 | GLM-5.3 Flash (Max) | 57.61 |
| 8 | Gemini 3.7 Flash (High) | 56.71 |
| 9 | Gemini 3.1 Pro (Preview) (High) | 56.34 |
| 10 | DeepSeek V4 Pro (0813) (Max) | 56.15 |
| 11 | Qwen 3.8 Max (xHigh) | 55.61 |
| 12 | Grok 4.6 (High) | 53.17 |
| 13 | DeepSeek V4 Flash (0731) (Max) | 51.48 |
| 14 | GPT-5.6 Luna (xHigh) | 47.86 |
| 15 | Qwen 3.8 27B (xHigh) | 43.05 |
Interactive version: theaggregate.ai/benchmark?slug=llm2014-logic-2026-09 · How It Works · Data refreshed daily, snapshot 2026-09-05.