Biomedicine on Biomedicine
55.8ScoreGPT-5
Evaluation results
| Method | Links | ||
|---|---|---|---|
| GPT-5Generation Mode=Standard LLM2026.01 | 55.8 | — | |
| GPT-5Generation Mode=LLM-in-Sandbox2026.01 | 49 | -6.8 | |
| DeepSeek-V3.2-ThinkingGeneration Mode=LLM-in-Sandbox2026.01 | 41.6 | 2.8 | |
| Kimi-K2-ThinkingGeneration Mode=Standard LLM2026.01 | 40.4 | — | |
| DeepSeek-V3.2-ThinkingGeneration Mode=Standard LLM2026.01 | 38.8 | — | |
| Claude-Sonnet-4.5-ThinkGeneration Mode=LLM-in-Sandbox2026.01 | 38 | 1 | |
| Claude-Sonnet-4.5-ThinkGeneration Mode=Standard LLM2026.01 | 37 | — | |
| Kimi-K2-ThinkingGeneration Mode=LLM-in-Sandbox2026.01 | 35.4 | -5 | |
| MiniMax-M2Generation Mode=LLM-in-Sandbox2026.01 | 28.2 | 2 | |
| MiniMax-M2Generation Mode=Standard LLM2026.01 | 26.2 | — | |
| Qwen3-Coder-30B-A3BGeneration Mode=LLM-in-Sandbox2026.01 | 18.2 | 3.8 | |
| Qwen3-Coder-30B-A3BGeneration Mode=Standard LLM2026.01 | 14.4 | — | |
| Qwen3-4B-Instruct-2507Generation Mode=Standard LLM2026.01 | 10.2 | — | |
| Qwen3-4B-Instruct-2507Generation Mode=LLM-in-Sandbox2026.01 | 9.4 | -0.8 |