List your company

State Updating on AMA-Bench (SU)

58.73Success MetricQWEN3.5-397B-A17B
23.047632.311341.57550.8387Jun 16, 2026

Evaluation results

MethodLinks
QWEN3.5-397B-A17BBackbone LLM=QWEN3.5-397B-A17B2026.0658.73
OPD-Evolver-9BBackbone LLM=QWEN3.5-9B2026.0653.94
MemEvolveBackbone LLM=QWEN3.5-9B2026.0649.77
CheatsheetBackbone LLM=QWEN3.5-9B2026.0649.3
AWMBackbone LLM=QWEN3.5-9B2026.0648.38
ReasoningBankBackbone LLM=QWEN3.5-9B2026.0648.38
No MemoryBackbone LLM=QWEN3.5-9B2026.0647.14
MempBackbone LLM=QWEN3.5-9B2026.0647.14
STEP-3.5-FLASH (196B)Backbone LLM=STEP-3.5-FLASH (196B)2026.0646.99
ExpeLBackbone LLM=QWEN3.5-9B2026.0643.74
EvolveRBackbone LLM=QWEN3.5-9B2026.0642.81
OPD-Evolver-4BBackbone LLM=QWEN3-4B2026.0634.93
MemEvolveBackbone LLM=QWEN3-4B2026.0631.53
CheatsheetBackbone LLM=QWEN3-4B2026.0630.91
AWMBackbone LLM=QWEN3-4B2026.0630.14
ReasoningBankBackbone LLM=QWEN3-4B2026.0629.68
MempBackbone LLM=QWEN3-4B2026.0628.44
No MemoryBackbone LLM=QWEN3-4B2026.0627.67
ExpeLBackbone LLM=QWEN3-4B2026.0624.88
EvolveRBackbone LLM=QWEN3-4B2026.0624.42