LLM2014 Logic 2026-07: leaderboard
Metric: Median Score. Source: raw.githubusercontent.com. 45 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 (xHigh) | 77.46 |
| 2 | Kimi K3 (Max) | 74.8 |
| 3 | GPT-5.6 Sol (xHigh) | 72.99 |
| 4 | Claude Opus 5 (xHigh) | 71.88 |
| 5 | DeepSeek V4 Flash (0731) (Max) | 58.8 |
| 6 | Gemini 3.1 Pro (Preview) (High) | 58.46 |
| 7 | GLM-5.2 (Max) | 58.27 |
| 8 | Muse Spark 1.1 | 57.23 |
| 9 | Grok 4.5 (High) | 56.72 |
| 10 | GPT-5.6 Luna (xHigh) | 51.97 |
| 11 | Claude Sonnet 5 (xHigh) | 43.14 |
| 12 | Gemini 3.6 Flash (High) | 41.74 |
| 13 | MiniMax-M3 | 40.94 |
| 14 | Claude Opus 5 | 31.73 |
| 15 | Gemini 3.5 Flash Lite (High) | 22.82 |
Interactive version: theaggregate.ai/benchmark?slug=llm2014-logic-2026-07 · How It Works · Data refreshed daily, snapshot 2026-09-05.