LiveBench Data Analysis: leaderboard
Metric: Score. Source: livebench.ai. Saturation forecast: Around April 2028. 36 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 4 Argon | 85.2 | #7 |
| 2 | GPT-6 Astra | 83 | #5 |
| 3 | GPT-6.1 Sol | 82.7 | #9 |
| 4 | GPT-5.5 | 81.6 | #30 |
| 5 | GPT-6 Sol | 81.2 | #16 |
| 6 | Claude Fable 5 | 80.5 | #15 |
| 7 | Claude Opus 5.5 | 80.3 | #3 |
| 8 | Claude Fable 5.1 | 80.3 | #8 |
| 9 | GPT-5.6 Sol | 79.8 | #18 |
| 10 | Muse Spark 1.3 | 79.6 | #25 |
| 11 | GPT-5.6 Terra | 79.3 | #42 |
| 12 | DeepSeek V4.1 Flash | 79.3 | #39 |
| 13 | Kimi K3 | 78.7 | #29 |
| 14 | Gemini 3.1 Pro (Preview) | 78.5 | #57 |
| 15 | Qwen 3.8 Max | 78.4 | #32 |
No result here: #10 Muse Wonder Full.
Interactive version: theaggregate.ai/benchmark?slug=livebench-data-analysis · How It Works · Data refreshed daily, snapshot 2026-10-14.