LiveBench: leaderboard
Continuously updated benchmark measuring many capabilities. Sort models by weighted score or sub-task scores. Tests math, coding, reasoning, language, instruction following, and data analysis.
Metric: LiveBench average (imported). Source: livebench.ai. Source: benchmarklist.com. Saturation forecast: Around July 2027. 48 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.5 (xHigh) | 81.28 | #31 (GPT-5.5) |
| 2 | GPT-5.4 (xHigh) | 80.91 | #79 (GPT-5.4) |
| 3 | Gemini 3.1 Pro (Preview) (High) | 80.71 | #58 (Gemini 3.1 Pro (Preview)) |
| 4 | Claude Fable 5 (xHigh) | 78.57 | #16 (Claude Fable 5) |
| 5 | Claude Opus 4.8 (xHigh) | 77.55 | #37 (Claude Opus 4.8) |
| 6 | Claude Opus 4.7 (xHigh) | 77.1 | #49 (Claude Opus 4.7) |
| 7 | Claude Opus 4.6 (Thinking, High) | 76.79 | #63 (Claude Opus 4.6) |
| 8 | Claude Opus 4.8 (High) | 76.18 | #37 (Claude Opus 4.8) |
| 9 | Gemini 3.5 Flash (High) | 75.79 | #60 (Gemini 3.5 Flash) |
| 10 | Claude Fable 5 (High) | 75.74 | #16 (Claude Fable 5) |
| 11 | GPT-5.4 (High) | 75.6 | #79 (GPT-5.4) |
| 12 | GPT-5.2 (2025-12-11) (High) | 75.38 | |
| 13 | Qwen 3.7 Max | 75.15 | #75 |
| 14 | Claude Opus 4.7 (High) | 74.66 | #49 (Claude Opus 4.7) |
| 15 | DeepSeek V4 Pro | 74.39 | #102 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=livebench · How It Works · Data refreshed daily, snapshot 2026-10-20.