LLM Stats (ERQA) — leaderboard
Metric: Score (%). Source: llm-stats.com. 22 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Seed 2.1 Pro | 72 |
| 2 | Qwen 3.7 Plus | 69.8 |
| 3 | GPT-5 | 65.7 |
| 4 | Qwen 3.6 Plus | 65.7 |
| 5 | Qwen 3.5 35B A3B | 64.8 |
| 6 | Muse Spark | 64.7 |
| 7 | O3 | 64 |
| 8 | Qwen 3.6 27B | 62.5 |
| 9 | Qwen 3.5 122B A10B | 62 |
| 10 | Qwen 3.5 27B | 60.5 |
| 11 | Qwen 3 VL 235B A22B (Thinking) | 52.5 |
| 12 | Qwen 3 VL 32B (Thinking) | 52.3 |
| 13 | Qwen 3 VL 235B A22B Instruct | 51.3 |
| 14 | Qwen 3 VL 32B Instruct | 48.8 |
| 15 | Qwen 3 VL 4B (Thinking) | 47.3 |
Interactive version: theaggregate.ai/benchmark?slug=llm-stats-erqa · How the rankings work · Data refreshed daily, snapshot 2026-07-22.