List your company

Text Generation on GSM8K

187.43Throughput (tokens/s)EVICT
59.686892.8509126.015159.1791May 1, 2026

Evaluation results

MethodLinks
EVICTTemperature=0, Backbone=Qwen3-235B-A22B, Inference Engine=SGLang, Hardware=NVIDIA A100 SXM4 80GB GPUs, Batch Size=1, Tensor Parallelism=TP=82026.05187.43——————
EVICTTemperature=1, Backbone=Qwen3-235B-A22B, Inference Engine=SGLang, Hardware=NVIDIA A100 SXM4 80GB GPUs, Batch Size=1, Tensor Parallelism=TP=82026.05184.44——————
EAGLE-3Temperature=0, Backbone=Qwen3-235B-A22B, Inference Engine=SGLang, Hardware=NVIDIA A100 SXM4 80GB GPUs, Batch Size=1, Tensor Parallelism=TP=82026.05146.38——————
EAGLE-3Temperature=1, Backbone=Qwen3-235B-A22B, Inference Engine=SGLang, Hardware=NVIDIA A100 SXM4 80GB GPUs, Batch Size=1, Tensor Parallelism=TP=82026.05143.43——————
DDDTemperature=0, Backbone=Qwen3-235B-A22B, Inference Engine=SGLang, Hardware=NVIDIA A100 SXM4 80GB GPUs, Batch Size=1, Tensor Parallelism=TP=82026.05137.71——————
DDDTemperature=1, Backbone=Qwen3-235B-A22B, Inference Engine=SGLang, Hardware=NVIDIA A100 SXM4 80GB GPUs, Batch Size=1, Tensor Parallelism=TP=82026.05135.65——————
VanillaTemperature=0, Backbone=Qwen3-235B-A22B, Inference Engine=SGLang, Hardware=NVIDIA A100 SXM4 80GB GPUs, Batch Size=1, Tensor Parallelism=TP=82026.0579.61——————
VanillaTemperature=1, Backbone=Qwen3-235B-A22B, Inference Engine=SGLang, Hardware=NVIDIA A100 SXM4 80GB GPUs, Batch Size=1, Tensor Parallelism=TP=82026.0579.01——————
LookaheadTemperature=0, Backbone=Qwen3-235B-A22B, Inference Engine=SGLang, Hardware=NVIDIA A100 SXM4 80GB GPUs, Batch Size=1, Tensor Parallelism=TP=82026.0565.5——————
LookaheadTemperature=1, Backbone=Qwen3-235B-A22B, Inference Engine=SGLang, Hardware=NVIDIA A100 SXM4 80GB GPUs, Batch Size=1, Tensor Parallelism=TP=82026.0564.6——————
ARBackbone=Qwen3-4B, Temperature=1.02026.06——31.05————
ARBackbone=Qwen3-8B, Temperature=1.02026.06——30.84————
CADDTREEBackbone=Qwen3-4B, Temperature=1.02026.06——5.568.67—250—
CADDTREEBackbone=Qwen3-8B, Temperature=1.02026.06——5.628.44—184—
DDTree-oracleBackbone=Qwen3-4B, Temperature=1.02026.06——5.58.65256——
DDTree-oracleBackbone=Qwen3-8B, Temperature=1.02026.06——5.678.27128——
DFlashBackbone=Qwen3-4B, Temperature=1.02026.06——7.646———
DFlashBackbone=Qwen3-8B, Temperature=1.02026.06——7.695.92———