List your company
ResearchFormerly WizWand

Reasoning on LiveCodeBench (LCB) 2024.10-2025.02

58.46Pass@1FP16
18.877629.153839.4349.7062May 9, 2026
Updated 5mo ago

Evaluation results

MethodLinks
FP16Model=Qwen3-8B, Speedup=1.0×2026.0558.46
LAQuantModel=Qwen3-8B, Quantization Bit-width=4-bit, Group Size=128, Speedup=2.45×2026.0556.69
ParoQ++Model=Qwen3-8B, Quantization Bit-width=4-bit, Group Size=128, Speedup=2.32×2026.0555.72
ParoQModel=Qwen3-8B, Quantization Bit-width=4-bit, Group Size=128, Speedup=2.32×2026.0555.47
FP16Model=Qwen3-4B, Speedup=1.0×2026.0554.48
GPTQModel=Qwen3-8B, Quantization Bit-width=4-bit, Group Size=128, Speedup=2.45×2026.0552.99
LAQuantModel=Qwen3-4B, Quantization Bit-width=4-bit, Group Size=128, Speedup=2.0×2026.0552.74
ParoQ++Model=Qwen3-4B, Quantization Bit-width=4-bit, Group Size=128, Speedup=1.84×2026.0551.62
R-QATModel=Qwen3-8B, Quantization Bit-width=4-bit, Group Size=128, Speedup=2.45×2026.0551.62
ParoQModel=Qwen3-4B, Quantization Bit-width=4-bit, Group Size=128, Speedup=1.84×2026.0550
GPTQModel=Qwen3-4B, Quantization Bit-width=4-bit, Group Size=128, Speedup=2.0×2026.0548.75
R-QATModel=Qwen3-4B, Quantization Bit-width=4-bit, Group Size=128, Speedup=2.0×2026.0546.76
FP16Model=R1-Distill-Llama-8B, Speedup=1.0×2026.0536.32
LAQuantModel=R1-Distill-Llama-8B, Quantization Bit-width=4-bit, Group Size=128, Speedup=2.46×2026.0535.7
ParoQ++Model=R1-Distill-Llama-8B, Quantization Bit-width=4-bit, Group Size=128, Speedup=2.33×2026.0535.45
R-QATModel=R1-Distill-Llama-8B, Quantization Bit-width=4-bit, Group Size=128, Speedup=2.46×2026.0534.33
GPTQModel=R1-Distill-Llama-8B, Quantization Bit-width=4-bit, Group Size=128, Speedup=2.46×2026.0534.21
FP16Model=Qwen3-1.7B, Speedup=1.0×2026.0533.71
ParoQModel=R1-Distill-Llama-8B, Quantization Bit-width=4-bit, Group Size=128, Speedup=2.33×2026.0533.33
LAQuantModel=Qwen3-1.7B, Quantization Bit-width=4-bit, Group Size=128, Speedup=1.64×2026.0531.84
ParoQ++Model=Qwen3-1.7B, Quantization Bit-width=4-bit, Group Size=128, Speedup=1.48×2026.0528.98
ParoQModel=Qwen3-1.7B, Quantization Bit-width=4-bit, Group Size=128, Speedup=1.48×2026.0528.61
R-QATModel=Qwen3-1.7B, Quantization Bit-width=4-bit, Group Size=128, Speedup=1.64×2026.0525.87
GPTQModel=Qwen3-1.7B, Quantization Bit-width=4-bit, Group Size=128, Speedup=1.64×2026.0520.4