Question Answering on RadioBench Task Level 1
96PU ScoreClaude-Opus-4.6
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| Claude-Opus-4.6Category=Foundation Models2026.06 | 96 | 97 | 97 | 75 | 91 | |
| GPT-5.3-CodexCategory=Foundation Models2026.06 | 94 | 98 | 96 | 69 | 89 | |
| IoTPilotCategory=Open-Source Multi-Agent Systems2026.06 | 94 | 98 | 97 | 72 | 90 | |
| RadioMasterCategory=Open-Source Multi-Agent Systems2026.06 | 94 | 97 | 94 | 91 | 94 | |
| Qwen3-MaxCategory=Foundation Models2026.06 | 91 | 97 | 96 | 70 | 89 | |
| AutoIoTCategory=Open-Source Multi-Agent Systems2026.06 | 91 | 91 | 94 | 55 | 83 | |
| DeepSeek-V3.2Category=Foundation Models2026.06 | 87 | 94 | 90 | 55 | 82 | |
| Gemini3.1 ProCategory=Foundation Models2026.06 | 77 | 77 | 78 | 69 | 75 | |
| MiniMax-M2.5Category=Foundation Models2026.06 | 50 | 48 | 54 | 39 | 48 |