List your company

Code Generation on KodCode (test)

61.13AccuracyFlashMem
21.318831.654441.9952.3256Jan 9, 2026

Evaluation results

MethodLinks
FlashMemModel Backbone=Qwen 3 4B Instruct, Inference Strategy=FlashMem2026.0161.13
MemGenModel Backbone=Qwen 3 4B Instruct, Inference Strategy=MemGen2026.0159.77
CoT-SCModel Backbone=Qwen 3 4B Instruct, Inference Strategy=CoT-SC2026.0157.55
VanillaModel Backbone=Qwen 3 4B Instruct, Inference Strategy=Vanilla2026.0156.48
MemGenModel Backbone=Qwen 2.5 1.5B Instruct, Inference Strategy=MemGen2026.0155.7
FlashMemModel Backbone=Qwen 2.5 1.5B Instruct, Inference Strategy=FlashMem2026.0150.2
SnapKVModel Backbone=Qwen 3 4B Instruct, Inference Strategy=SnapKV2026.0149.7
SnapKVModel Backbone=Qwen 2.5 1.5B Instruct, Inference Strategy=SnapKV2026.0139.7
CoT-SCModel Backbone=Qwen 2.5 1.5B Instruct, Inference Strategy=CoT-SC2026.0129.3
VanillaModel Backbone=Qwen 2.5 1.5B Instruct, Inference Strategy=Vanilla2026.0122.85