List your company

Text Generation on Math-500 (Throughput/Speed)

1,094.6Throughput (TPS)JetFlow
89.128350.164611.2872.236Jun 16, 2026

Evaluation results

MethodLinks
JetFlowBatch Size=16, Tree Budget=32, Model=Qwen3-8B, Hardware=single H100 GPU2026.061,094.63.81
JetFlowBatch Size=16, Tree Budget=64, Model=Qwen3-8B, Hardware=single H100 GPU2026.06995.83.47
JetFlowBatch Size=16, Tree Budget=16, Model=Qwen3-8B, Hardware=single H100 GPU2026.06891.83.1
JetFlowBatch Size=8, Tree Budget=64, Model=Qwen3-8B, Hardware=single H100 GPU2026.06859.33.49
JetFlowBatch Size=8, Tree Budget=32, Model=Qwen3-8B, Hardware=single H100 GPU2026.06839.33.41
JetFlowBatch Size=8, Tree Budget=128, Model=Qwen3-8B, Hardware=single H100 GPU2026.06803.53.26
JetFlowBatch Size=16, Tree Budget=128, Model=Qwen3-8B, Hardware=single H100 GPU2026.06803.12.8
JetFlowBatch Size=4, Tree Budget=128, Model=Qwen3-8B, Hardware=single H100 GPU2026.06742.93.64
JetFlowBatch Size=8, Tree Budget=16, Model=Qwen3-8B, Hardware=single H100 GPU2026.06679.32.76
JetFlowBatch Size=4, Tree Budget=64, Model=Qwen3-8B, Hardware=single H100 GPU2026.06664.23.26
JetFlowBatch Size=2, Tree Budget=128, Model=Qwen3-8B, Hardware=single H100 GPU2026.06621.63.81
JetFlowBatch Size=1, Tree Budget=128, Model=Qwen3-8B, Hardware=single H100 GPU2026.06553.34.33
JetFlowBatch Size=4, Tree Budget=32, Model=Qwen3-8B, Hardware=single H100 GPU2026.06534.22.62
JetFlowBatch Size=2, Tree Budget=64, Model=Qwen3-8B, Hardware=single H100 GPU2026.065163.16
JetFlowBatch Size=1, Tree Budget=64, Model=Qwen3-8B, Hardware=single H100 GPU2026.06447.33.5
JetFlowBatch Size=4, Tree Budget=16, Model=Qwen3-8B, Hardware=single H100 GPU2026.06433.62.13
JetFlowBatch Size=2, Tree Budget=32, Model=Qwen3-8B, Hardware=single H100 GPU2026.06360.32.21
JetFlowBatch Size=1, Tree Budget=32, Model=Qwen3-8B, Hardware=single H100 GPU2026.063122.44
ARBatch Size=16, Model=Qwen3-8B, Hardware=single H100 GPU2026.06287.3—
JetFlowBatch Size=2, Tree Budget=16, Model=Qwen3-8B, Hardware=single H100 GPU2026.06266.21.63
ARBatch Size=8, Model=Qwen3-8B, Hardware=single H100 GPU2026.06246.2—
JetFlowBatch Size=1, Tree Budget=16, Model=Qwen3-8B, Hardware=single H100 GPU2026.062241.75
ARBatch Size=4, Model=Qwen3-8B, Hardware=single H100 GPU2026.06203.8—
ARBatch Size=2, Model=Qwen3-8B, Hardware=single H100 GPU2026.06163.3—
ARBatch Size=1, Model=Qwen3-8B, Hardware=single H100 GPU2026.06127.8—