Chemistry on Chemistry tasks
84.4ScoreClaude-Sonnet-4.5-Think
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Claude-Sonnet-4.5-ThinkGeneration Mode=LLM-in-Sandbox2026.01 | 84.4 | 1.1 | |
| Claude-Sonnet-4.5-ThinkGeneration Mode=Standard LLM2026.01 | 83.3 | — | |
| GPT-5Generation Mode=LLM-in-Sandbox2026.01 | 81.6 | 0.5 | |
| GPT-5Generation Mode=Standard LLM2026.01 | 81.1 | — | |
| DeepSeek-V3.2-ThinkingGeneration Mode=LLM-in-Sandbox2026.01 | 77.8 | 1.1 | |
| Kimi-K2-ThinkingGeneration Mode=LLM-in-Sandbox2026.01 | 77.6 | 3.2 | |
| DeepSeek-V3.2-ThinkingGeneration Mode=Standard LLM2026.01 | 76.7 | — | |
| Kimi-K2-ThinkingGeneration Mode=Standard LLM2026.01 | 74.4 | — | |
| MiniMax-M2Generation Mode=LLM-in-Sandbox2026.01 | 68.4 | 14.4 | |
| Qwen3-4B-Instruct-2507Generation Mode=Standard LLM2026.01 | 56.4 | — | |
| MiniMax-M2Generation Mode=Standard LLM2026.01 | 54 | — | |
| Qwen3-Coder-30B-A3BGeneration Mode=LLM-in-Sandbox2026.01 | 54 | 5.3 | |
| Qwen3-4B-Instruct-2507Generation Mode=LLM-in-Sandbox2026.01 | 49.3 | -7.1 | |
| Qwen3-Coder-30B-A3BGeneration Mode=Standard LLM2026.01 | 48.7 | — |