List your company

Mathematical Reasoning on GK EN 2023 (test)

77.9Pass@1Transformers
45.76454.10762.4570.793Jan 26, 2026

Evaluation results

MethodLinks
TransformersBackbone=R1-Qwen2026.0177.9593.7
DYNTSBackbone=R1-Qwen2026.0176.4788.5
R-KVBackbone=R1-Qwen2026.0175.8792.8
SnapKVBackbone=R1-Qwen2026.0174.9787.4
H2OBackbone=R1-Qwen2026.0174.1780.1
TransformersBackbone=R1-Llama2026.0173.1390.9
DYNTSBackbone=R1-Llama2026.0172.3631.8
SepLLMBackbone=R1-Qwen2026.0172820.1
WindowBackbone=R1-Qwen2026.0171.8815.2
R-KVBackbone=R1-Llama2026.0171.4622.6
StreamingLLMBackbone=R1-Qwen2026.0171.2824
SnapKVBackbone=R1-Llama2026.0168.7615.7
H2OBackbone=R1-Llama2026.0167.5601.8
SepLLMBackbone=R1-Llama2026.0161.4635
StreamingLLMBackbone=R1-Llama2026.0153.4624.6
WindowBackbone=R1-Llama2026.0147622.6