Functional Group Reasoning (Binary Classification) on FGBench Interaction
81.9AccuracyLFM2-2.6B-MMAI
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| LFM2-2.6B-MMAITraining=ST, Reasoning=/think2026.03 | 81.9 | 100 | |
| LFM2-2.6B-MMAITraining=MT, Reasoning=/think2026.03 | 81.5 | 100 | |
| LFM2-2.6B-MMAITraining=MT, Reasoning=/no think2026.03 | 80.8 | 100 | |
| LFM2-2.6B-MMAITraining=ST, Reasoning=/no think2026.03 | 80.8 | 100 | |
| Opus-4-5Class=Proprietary LLM2026.03 | 72.9 | 100 | |
| LFM2-2.6BClass=Liquid Foundation Model2026.03 | 72.4 | 100 | |
| Sonnet-4-5Class=Proprietary LLM2026.03 | 60.6 | 99.9 | |
| Llama-3.1Parameters=8B2026.03 | 54.7 | 98.2 | |
| GPT-5-2Class=Proprietary LLM2026.03 | 53.1 | 100 | |
| Llama-3.1Parameters=70B2026.03 | 53 | 100 | |
| GPT-5-1Class=Proprietary LLM2026.03 | 52.6 | 100 | |
| DeepSeek-3-2Class=Open-weight LLM2026.03 | 47.6 | 89.6 | |
| Qwen2.5-7BClass=Open-weight LLM2026.03 | 39.6 | 99.9 | |
| LlaSMol-Mistral-7BClass=Foundational LLM for Chemistry2026.03 | 29.8 | 96.8 | |
| ChemLLM-7BClass=Foundational LLM for Chemistry2026.03 | 23.5 | 99.7 | |
| Llama-3-8B-MolInstClass=Foundational LLM for Chemistry2026.03 | 5.9 | 14.9 |