Global AI MapTop Frontier Leaderboard
LiveBench weighted overall scores from the benchmark’s published release. Suite weights and available-score handling follow the source; this is not a universal intelligence ranking.
Build snapshot retrieved 2026-10-30T22:39:25.727891+00:00. Live data loads in your browser.
| RANK | SYSTEM / MODEL | SCORE | CONTEXT |
|---|---|---|---|
| 01 | claude-fable-5.1 ↗ | 85.69 | LiveBench release 20261025 · published suite weights; mean over available suites 20261025 |
| 02 | gpt-6-astra ↗ | 85.64 | LiveBench release 20261025 · published suite weights; mean over available suites 20261025 |
| 03 | claude-opus-5.5 ↗ | 85.14 | LiveBench release 20261025 · published suite weights; mean over available suites 20261025 |
| 04 | gpt-6.1-sol ↗ | 84.07 | LiveBench release 20261025 · published suite weights; mean over available suites 20261025 |
| 05 | claude-sonnet-5.5 ↗ | 80.04 | LiveBench release 20261025 · published suite weights; mean over available suites 20261025 |
| 06 | gemini-4-argon ↗ | 79.30 | LiveBench release 20261025 · published suite weights; mean over available suites 20261025 |
| 07 | gpt-6.1-terra ↗ | 77.79 | LiveBench release 20261025 · published suite weights; mean over available suites 20261025 |
| 08 | muse-wonder-1.0 ↗ | 74.15 | LiveBench release 20261025 · published suite weights; mean over available suites 20261025 |
| 09 | deepseek-v4.1-flash-1017 ↗ | 72.87 | LiveBench release 20261025 · published suite weights; mean over available suites 20261025 |
| 10 | kimi-k3.1-pro ↗ | 71.29 | LiveBench release 20261025 · published suite weights; mean over available suites 20261025 |
| 11 | grok-4.7 ↗ | 70.14 | LiveBench release 20261025 · published suite weights; mean over available suites 20261025 |
| 12 | claude-haiku-5.5 ↗ | 69.85 | LiveBench release 20261025 · published suite weights; mean over available suites 20261025 |
| 13 | mimo-v2.6-pro ↗ | 68.48 | LiveBench release 20261025 · published suite weights; mean over available suites 20261025 |
| 14 | gpt-5.6-terra ↗ | 67.79 | LiveBench release 20261025 · published suite weights; mean over available suites 20261025 |
| 15 | grok-4.6 ↗ | 67.75 | LiveBench release 20261025 · published suite weights; mean over available suites 20261025 |
| 16 | minimax-m3.1-flash ↗ | 66.89 | LiveBench release 20261025 · published suite weights; mean over available suites 20261025 |
| 17 | gpt-6-luna ↗ | 64.59 | LiveBench release 20261025 · published suite weights; mean over available suites 20261025 |
| 18 | kimi-k3 ↗ | 64.57 | LiveBench release 20261025 · published suite weights; mean over available suites 20261025 |
| 19 | mistral-large-4-0 ↗ | 63.49 | LiveBench release 20261025 · published suite weights; mean over available suites 20261025 |
| 20 | muse-spark-1.3 ↗ | 63.03 | LiveBench release 20261025 · published suite weights; mean over available suites 20261025 |
Method, limits & original data
LiveBench weighted overall scores from the benchmark’s published release. Suite weights and available-score handling follow the source; this is not a universal intelligence ranking.
Rows are ranked within this benchmark. Different hardware, model versions, harnesses and test conditions can change results. A blank or absent score is never treated as zero. Ties retain equal rank in the interactive view.
Additional benchmark references: Arena · Artificial Analysis · Terminal-Bench. Keyed APIs are not exposed in this website.