List your company

Causal Inference on AMA-Bench (CI)

57.21Success MetricQWEN3.5-397B-A17B
23.534832.277441.0249.7626Jun 16, 2026

Evaluation results

MethodLinks
QWEN3.5-397B-A17BBackbone LLM=QWEN3.5-397B-A17B2026.0657.21
STEP-3.5-FLASH (196B)Backbone LLM=STEP-3.5-FLASH (196B)2026.0649.5
OPD-Evolver-9BBackbone LLM=QWEN3.5-9B2026.0647.32
MempBackbone LLM=QWEN3.5-9B2026.0645.81
MemEvolveBackbone LLM=QWEN3.5-9B2026.0644.3
AWMBackbone LLM=QWEN3.5-9B2026.0643.96
ReasoningBankBackbone LLM=QWEN3.5-9B2026.0642.28
EvolveRBackbone LLM=QWEN3.5-9B2026.0641.78
ExpeLBackbone LLM=QWEN3.5-9B2026.0641.11
CheatsheetBackbone LLM=QWEN3.5-9B2026.0640.77
No MemoryBackbone LLM=QWEN3.5-9B2026.0640.1
OPD-Evolver-4BBackbone LLM=QWEN3-4B2026.0632.89
MempBackbone LLM=QWEN3-4B2026.0632.38
MemEvolveBackbone LLM=QWEN3-4B2026.0629.53
AWMBackbone LLM=QWEN3-4B2026.0628.36
ReasoningBankBackbone LLM=QWEN3-4B2026.0627.35
EvolveRBackbone LLM=QWEN3-4B2026.0626.51
ExpeLBackbone LLM=QWEN3-4B2026.0626.17
CheatsheetBackbone LLM=QWEN3-4B2026.0625.34
No MemoryBackbone LLM=QWEN3-4B2026.0624.83