LLM Stats (RealWorldQA) — leaderboard
Metric: Score (%). Source: llm-stats.com. 25 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3.7 Plus | 86.9 |
| 2 | Seed 2.1 Pro | 86.7 |
| 3 | Qwen 3.6 Plus | 85.4 |
| 4 | Qwen 3.6 35B A3B | 85.3 |
| 5 | Qwen 3.5 122B A10B | 85.1 |
| 6 | Qwen 3.5 35B A3B | 84.1 |
| 7 | Qwen 3.6 27B | 84.1 |
| 8 | Qwen 3.5 27B | 83.7 |
| 9 | Qwen 3 VL 235B A22B (Thinking) | 81.3 |
| 10 | Qwen 3 VL 235B A22B Instruct | 79.3 |
| 11 | Qwen 3 VL 32B Instruct | 79 |
| 12 | Qwen 3 VL 32B (Thinking) | 78.4 |
| 13 | Qwen 2 VL 72B Instruct | 77.8 |
| 14 | Qwen 3 VL 30B A3B (Thinking) | 77.4 |
| 15 | Qwen 3 VL 30B A3B Instruct | 73.7 |
Interactive version: theaggregate.ai/benchmark?slug=llm-stats-realworldqa · How the rankings work · Data refreshed daily, snapshot 2026-07-22.