Causal Inference on AMA-Bench (CI)
57.21Success MetricQWEN3.5-397B-A17B
Evaluation Results
| Method | Links | |
|---|---|---|
| QWEN3.5-397B-A17BBackbone LLM=QWEN3.5-397B-A17B2026.06 | 57.21 | |
| STEP-3.5-FLASH (196B)Backbone LLM=STEP-3.5-FLASH (196B)2026.06 | 49.5 | |
| OPD-Evolver-9BBackbone LLM=QWEN3.5-9B2026.06 | 47.32 | |
| MempBackbone LLM=QWEN3.5-9B2026.06 | 45.81 | |
| MemEvolveBackbone LLM=QWEN3.5-9B2026.06 | 44.3 | |
| AWMBackbone LLM=QWEN3.5-9B2026.06 | 43.96 | |
| ReasoningBankBackbone LLM=QWEN3.5-9B2026.06 | 42.28 | |
| EvolveRBackbone LLM=QWEN3.5-9B2026.06 | 41.78 | |
| ExpeLBackbone LLM=QWEN3.5-9B2026.06 | 41.11 | |
| CheatsheetBackbone LLM=QWEN3.5-9B2026.06 | 40.77 | |
| No MemoryBackbone LLM=QWEN3.5-9B2026.06 | 40.1 | |
| OPD-Evolver-4BBackbone LLM=QWEN3-4B2026.06 | 32.89 | |
| MempBackbone LLM=QWEN3-4B2026.06 | 32.38 | |
| MemEvolveBackbone LLM=QWEN3-4B2026.06 | 29.53 | |
| AWMBackbone LLM=QWEN3-4B2026.06 | 28.36 | |
| ReasoningBankBackbone LLM=QWEN3-4B2026.06 | 27.35 | |
| EvolveRBackbone LLM=QWEN3-4B2026.06 | 26.51 | |
| ExpeLBackbone LLM=QWEN3-4B2026.06 | 26.17 | |
| CheatsheetBackbone LLM=QWEN3-4B2026.06 | 25.34 | |
| No MemoryBackbone LLM=QWEN3-4B2026.06 | 24.83 |