Qwen-AgentWorld: leaderboard
Metric: Overall (self-reported). Source: benchmarklist.com. 16 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.4 | 58.25 |
| 2 | Claude Opus 4.6 | 57.8 |
| 3 | Claude Opus 4.8 | 56.59 |
| 4 | Claude Sonnet 4.6 | 56.04 |
| 5 | Qwen 3.5 397B A17B | 54.74 |
| 6 | Gemini 3.1 Pro (Preview) | 54.57 |
| 7 | Kimi K2.6 | 53.42 |
| 8 | DeepSeek V4 Pro | 52.97 |
| 9 | Qwen 3.6 Max Preview | 52.42 |
| 10 | GLM-5.1 | 51.31 |
| 11 | Qwen 3.6 Plus | 50.81 |
| 12 | Qwen 3.5 35B A3B | 47.73 |
| 13 | MiniMax-M2.7 | 46.12 |
| 14 | Qwen 3.6 35B A3B | 42.88 |
Interactive version: theaggregate.ai/benchmark?slug=qwen-agentworld · How It Works · Data refreshed daily, snapshot 2026-09-05.