LiveBench Logic With Navigation: leaderboard
Metric: Score. Source: livebench.ai. 54 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Muse Spark 1.2 (xHigh) | 88 |
| 2 | GPT-6 (Max) | 88 |
| 3 | Claude Opus 5 (Max) | 86 |
| 4 | Claude Fable 5.1 (Max) | 86 |
| 5 | Claude Sonnet 5 (xHigh) | 86 |
| 6 | Qwen 3.7 Max | 84 |
| 7 | GPT-5.6 Sol (Max) | 82 |
| 8 | Grok 4.6 | 82 |
| 9 | Gemini 3.8 Flash (High) | 82 |
| 10 | GLM-5.2 | 80 |
| 11 | Kimi K3 | 80 |
| 12 | GPT-5.6 Luna (Max) | 80 |
| 13 | Claude Opus 4.6 (Thinking, High) | 80 |
| 14 | Claude Opus 4.8 (Max) | 78 |
| 15 | Claude Fable 5 (Max) | 78 |
Interactive version: theaggregate.ai/benchmark?slug=livebench-logic-with-navigation · How It Works · Data refreshed daily, snapshot 2026-09-05.