Mathematical Reasoning on MemoryArena Math
10.88Success ScoreOPD-Evolver-9B
Evaluation Results
| Method | Links | |
|---|---|---|
| OPD-Evolver-9BBackbone LLM=QWEN3.5-9B2026.06 | 10.88 | |
| ExpeLBackbone LLM=QWEN3.5-9B2026.06 | 8.19 | |
| AWMBackbone LLM=QWEN3.5-9B2026.06 | 7.34 | |
| CheatsheetBackbone LLM=QWEN3.5-9B2026.06 | 6.64 | |
| EvolveRBackbone LLM=QWEN3.5-9B2026.06 | 6.07 | |
| OPD-Evolver-4BBackbone LLM=QWEN3-4B2026.06 | 5.51 | |
| No MemoryBackbone LLM=QWEN3.5-9B2026.06 | 5.51 | |
| ReasoningBankBackbone LLM=QWEN3.5-9B2026.06 | 4.94 | |
| MempBackbone LLM=QWEN3.5-9B2026.06 | 4.8 | |
| MempBackbone LLM=QWEN3-4B2026.06 | 4.66 | |
| MemEvolveBackbone LLM=QWEN3.5-9B2026.06 | 4.24 | |
| QWEN3.5-397B-A17BBackbone LLM=QWEN3.5-397B-A17B2026.06 | 3.98 | |
| ReasoningBankBackbone LLM=QWEN3-4B2026.06 | 3.81 | |
| CheatsheetBackbone LLM=QWEN3-4B2026.06 | 2.97 | |
| No MemoryBackbone LLM=QWEN3-4B2026.06 | 2.4 | |
| STEP-3.5-FLASH (196B)Backbone LLM=STEP-3.5-FLASH (196B)2026.06 | 1.98 | |
| ExpeLBackbone LLM=QWEN3-4B2026.06 | 1.98 | |
| MemEvolveBackbone LLM=QWEN3-4B2026.06 | 1.84 | |
| AWMBackbone LLM=QWEN3-4B2026.06 | 1.69 | |
| EvolveRBackbone LLM=QWEN3-4B2026.06 | 1.27 |