FutureX — leaderboard
Metric: Overall Score (latest week, %). Source: futurex.live. 15 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3.7 Max | 49.33 |
| 2 | Grok 4.20 (Reasoning) | 47.22 |
| 3 | MiniMax-M3 | 46.75 |
| 4 | GPT-5.4 (High) | 46.09 |
| 5 | GPT-5.5 (High) | 45.84 |
| 6 | DeepSeek V3.2 (Thinking) | 45.81 |
| 7 | DeepSeek V4 Pro | 45.03 |
| 8 | DeepSeek V4 Flash | 44.07 |
| 9 | Gemini 3.1 Pro (Preview) (High) | 43.31 |
| 10 | Seed 2.0 Pro | 41.9 |
| 11 | Seed 2.0 Lite | 41.79 |
| 12 | MiniMax-M2.7 | 41.57 |
| 13 | Qwen 3.6 Max Preview | 39.04 |
| 14 | Gemini 3.5 Flash | 33.75 |
| 15 | Grok 4 | 16.84 |
Interactive version: aibenchmarks.dev/benchmark?slug=futurex · How the rankings work · Data refreshed daily, snapshot 2026-07-20.