Frontier llm models
Frontier llm modelsLiveBench Score
Claude Fable 5.1 Max Effort has the highest frontier llm models, at 83.4 LiveBench Score; Kimi K3 is lowest at 79.2 LiveBench Score.
The numbers
| 1 | Claude Fable 5.1 Max Effort | 83.4 |
| 2 | Claude 5.5 Opus Thinking Max Effort | 83.2 |
| 3 | Claude Fable 5 Max Effort | 83 |
| 4 | GPT-6 Astra Max Effort | 82.2 |
| 5 | GPT-6.1 Sol Max Effort | 81.6 |
| 6 | Muse Spark 1.3 xHigh Effort | 81.6 |
| 7 | DeepSeek V4.1 Flash Max Effort | 81.1 |
| 8 | GPT-5.6 Sol Max Effort | 81 |
| 9 | GPT-5.5 Thinking xHigh Effort | 80.2 |
| 10 | Claude 5 Opus Thinking Max Effort | 80.1 |
| 11 | GPT-6 Sol Max Effort | 79.3 |
| 12 | Kimi K3 | 79.2 |