Humanities Question Answering on HLE
13.37HLE ScoreUMEM-Llama-3.2-1B
Evaluation Results
| Method | Links | |
|---|---|---|
| UMEM-Llama-3.2-1BFrozen Executor=Gemini-2.5-Flash, Parameters=1B2026.02 | 13.37 | |
| UMEM-Qwen3-4BFrozen Executor=Gemini-2.5-Flash, Parameters=4B2026.02 | 11.76 | |
| MempFrozen Executor=Qwen3-8B-Thinking, Parameters=8B2026.02 | 11.22 | |
| ReMemFrozen Executor=Gemini-2.5-Flash, Parameters=API2026.02 | 10.7 | |
| MempFrozen Executor=GPT-5.1, Parameters=API2026.02 | 10.16 | |
| No MemoryFrozen Executor=Gemini-2.5-Flash, Parameters=-2026.02 | 10.16 | |
| Self-RAGFrozen Executor=Gemini-2.5-Flash, Parameters=API2026.02 | 10.16 | |
| Llama-3.2-1B-InstructFrozen Executor=Gemini-2.5-Flash, Parameters=1B2026.02 | 10.16 | |
| Qwen3-4B-InstructFrozen Executor=Gemini-2.5-Flash, Parameters=4B2026.02 | 9.63 | |
| Self-RAGFrozen Executor=Qwen3-8B-Thinking, Parameters=8B2026.02 | 8.56 | |
| ReMemFrozen Executor=GPT-5.1, Parameters=API2026.02 | 8.56 | |
| UMEM-Llama-3.2-1BFrozen Executor=GPT-5.1, Parameters=1B2026.02 | 8.56 | |
| UMEM-Qwen3-4BFrozen Executor=GPT-5.1, Parameters=4B2026.02 | 8.56 | |
| UMEM-Qwen3-4BFrozen Executor=Qwen3-8B-Thinking, Parameters=4B2026.02 | 8.02 | |
| Qwen3-4B-InstructFrozen Executor=GPT-5.1, Parameters=4B2026.02 | 8.02 | |
| No MemoryFrozen Executor=Qwen3-8B-Thinking, Parameters=-2026.02 | 7.51 | |
| Self-RAGFrozen Executor=GPT-5.1, Parameters=API2026.02 | 7.49 | |
| Llama-3.2-1B-InstructFrozen Executor=GPT-5.1, Parameters=1B2026.02 | 7.49 | |
| MempFrozen Executor=Gemini-2.5-Flash, Parameters=API2026.02 | 7.49 | |
| UMEM-Llama-3.2-1BFrozen Executor=Qwen3-8B-Thinking, Parameters=1B2026.02 | 6.95 | |
| Qwen3-4B-InstructFrozen Executor=Qwen3-8B-Thinking, Parameters=4B2026.02 | 6.95 | |
| No MemoryFrozen Executor=GPT-5.1, Parameters=-2026.02 | 6.95 | |
| ReMemFrozen Executor=Qwen3-8B-Thinking, Parameters=8B2026.02 | 6.42 | |
| Llama-3.2-1B-InstructFrozen Executor=Qwen3-8B-Thinking, Parameters=1B2026.02 | 6.42 |