List your company

Question Answering on GPQA Diamond (Accuracy and Performance)

86.3Throughput (Req/s)SQUEEZE EVOLVE (p=0)
-1.3221.427544.17566.9225Apr 9, 2026

Evaluation results

MethodLinks
SQUEEZE EVOLVE (p=0)Model 1=GPT-OSS-20B, Model 2=GPT-OSS-120B, Obs. M1 share=100%, GPU split (G2:G1)=0:162026.0486.32.8479
SQUEEZE EVOLVE (p=10)Model 1=GPT-OSS-20B, Model 2=GPT-OSS-120B, Obs. M1 share=87.5%, GPU split (G2:G1)=4:122026.0453.541.7679.5
RSAModel 1=GPT-OSS-20B, Model 2=GPT-OSS-120B, Obs. M1 share=0%, GPU split (G2:G1)=16:02026.0430.34179.6
SQUEEZE EVOLVE (p=0)Model 1=Qwen3-30B-A3B-I, Model 2=Qwen3-235B-A22B-I, Obs. M1 share=100%, GPU split (G2:G1)=0:162026.042210.7183.8
SQUEEZE EVOLVE (p=10)Model 1=Qwen3-30B-A3B-I, Model 2=Qwen3-235B-A22B-I, Obs. M1 share=87.5%, GPU split (G2:G1)=8:82026.048.173.9884
RSAModel 1=Qwen3-30B-A3B-I, Model 2=Qwen3-235B-A22B-I, Obs. M1 share=0%, GPU split (G2:G1)=16:02026.042.05184.3