State Updating on AMA-Bench (SU)
58.73Success MetricQWEN3.5-397B-A17B
Evaluation Results
| Method | Links | |
|---|---|---|
| QWEN3.5-397B-A17BBackbone LLM=QWEN3.5-397B-A17B2026.06 | 58.73 | |
| OPD-Evolver-9BBackbone LLM=QWEN3.5-9B2026.06 | 53.94 | |
| MemEvolveBackbone LLM=QWEN3.5-9B2026.06 | 49.77 | |
| CheatsheetBackbone LLM=QWEN3.5-9B2026.06 | 49.3 | |
| AWMBackbone LLM=QWEN3.5-9B2026.06 | 48.38 | |
| ReasoningBankBackbone LLM=QWEN3.5-9B2026.06 | 48.38 | |
| No MemoryBackbone LLM=QWEN3.5-9B2026.06 | 47.14 | |
| MempBackbone LLM=QWEN3.5-9B2026.06 | 47.14 | |
| STEP-3.5-FLASH (196B)Backbone LLM=STEP-3.5-FLASH (196B)2026.06 | 46.99 | |
| ExpeLBackbone LLM=QWEN3.5-9B2026.06 | 43.74 | |
| EvolveRBackbone LLM=QWEN3.5-9B2026.06 | 42.81 | |
| OPD-Evolver-4BBackbone LLM=QWEN3-4B2026.06 | 34.93 | |
| MemEvolveBackbone LLM=QWEN3-4B2026.06 | 31.53 | |
| CheatsheetBackbone LLM=QWEN3-4B2026.06 | 30.91 | |
| AWMBackbone LLM=QWEN3-4B2026.06 | 30.14 | |
| ReasoningBankBackbone LLM=QWEN3-4B2026.06 | 29.68 | |
| MempBackbone LLM=QWEN3-4B2026.06 | 28.44 | |
| No MemoryBackbone LLM=QWEN3-4B2026.06 | 27.67 | |
| ExpeLBackbone LLM=QWEN3-4B2026.06 | 24.88 | |
| EvolveRBackbone LLM=QWEN3-4B2026.06 | 24.42 |