Documentation quality evaluation on RAPID-IPN 1.0 (test)
71.52IDEAAegle
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| AegleMethod Category=Ours2026.04 | 71.52 | 63.92 | 79.93 | 24.24 | |
| ToTMethod Category=Reasoning-strategy baseline2026.04 | 67.58 | 63.96 | 79.86 | 21.77 | |
| MDAgentsMethod Category=Medical multi-agent system2026.04 | 66.58 | 60.98 | 79.95 | 21.28 | |
| CoTMethod Category=Reasoning-strategy baseline2026.04 | 65.61 | 61.89 | 78.57 | 21.23 | |
| MiniMax-M2Open-source=true2026.04 | 63.01 | 56.84 | 79.74 | 14.81 | |
| MedAgentsMethod Category=Medical multi-agent system2026.04 | 61.51 | 57.19 | 74.3 | 22.04 | |
| Qwen3-MaxProprietary=true2026.04 | 60.82 | 57.84 | 74.29 | 14.66 | |
| Kimi K2 ThinkingOpen-source=true2026.04 | 55.26 | 49.45 | 70.55 | 13.92 | |
| DeepSeek-V3.2Open-source=true2026.04 | 54.35 | 47.39 | 72.14 | 14.09 | |
| Lingshu-32BOpen-source=true, Medical-domain=true2026.04 | 51.41 | 47.89 | 72.07 | 8.62 | |
| Doubao-Seed-1.6Proprietary=true2026.04 | 51.11 | 44.37 | 68.35 | 14.38 | |
| Gemini 2.5Proprietary=true2026.04 | 49.89 | 39.03 | 71.25 | 14.69 | |
| DeepSeek-V3.2-ThinkingOpen-source=true2026.04 | 49.37 | 41.98 | 70.72 | 12.56 | |
| GLM-4.6Open-source=true2026.04 | 48.23 | 40.44 | 68.92 | 13.31 | |
| ERNIE-5.0-PreviewProprietary=true2026.04 | 45.05 | 40.03 | 67.03 | 12.41 | |
| GPT-4oProprietary=true2026.04 | 44.7 | 34.79 | 69.89 | 10.84 | |
| HuatuoGPT-o1-7BOpen-source=true, Medical-domain=true2026.04 | 41.89 | 40.28 | 68.58 | 6.66 | |
| Qwen3-8B-thinkOpen-source=true2026.04 | 39.93 | 28.92 | 66.14 | 6.89 | |
| Baichuan-M2-32BOpen-source=true, Medical-domain=true2026.04 | 39.4 | 31.54 | 65.42 | 9.24 |