List your company

General Reasoning on Overall (Efficiency Metrics)

84.8AccuracyDTSR
49.64858.77467.977.026Apr 6, 2026Apr 7, 2026Apr 8, 2026

Evaluation results

MethodLinks
DTSRBackbone=Qwen3-14B2026.0484.83,748——
VanillaBackbone=Qwen3-32B2026.0484.75,638——
DTSRBackbone=Qwen3-32B2026.0484.64,010——
VanillaBackbone=Qwen3-14B2026.0484.45,761——
VanillaModel=Qwen3-14B2026.0483.37,5321007,532
NoWAITBackbone=Qwen3-32B2026.0483.34,285——
NoWAITBackbone=Qwen3-14B2026.0483.24,584——
DEERBackbone=Qwen3-32B2026.0483.14,318——
DEERBackbone=Qwen3-14B2026.04834,367——
VanillaBackbone=Qwen3-8B2026.0481.96,510——
RCPDModel=Qwen3-14B2026.0481.57,09991.37,394
DTSRBackbone=Qwen3-8B2026.04814,428——
DEERModel=Qwen3-14B2026.0479.64,60555.34,684
DEERBackbone=Qwen3-8B2026.0479.34,532——
NoWAITBackbone=Qwen3-8B2026.0479.14,832——
EATModel=Qwen3-14B2026.0478.56,08682.76,293
VanillaModel=Qwen3-4B2026.0478.48,3441008,344
CoDE-StopModel=Qwen3-14B2026.04784,25650.14,330
RCPDModel=Qwen3-4B2026.0477.88,22196.98,565
DEERModel=Qwen3-4B2026.0477.46,176706,294
CoDE-StopModel=Qwen3-4B2026.0477.15,85965.45,956
EATModel=Qwen3-4B2026.0473.66,54778.56,777
NoThinkingBackbone=Qwen3-14B2026.0473.61,302——
VanillaModel=Nemotron-8B2026.0473.25,7291005,729
DEERModel=Nemotron-8B2026.04724,73680.84,830
RCPDModel=Nemotron-8B2026.0471.85,53696.25,776
Think or NotModel=Nemotron-8B2026.0471.75,02889.59,223
NoThinkingBackbone=Qwen3-32B2026.0471.61,123——
CoDE-StopModel=Nemotron-8B2026.0471.44,51675.44,607
EATModel=Nemotron-8B2026.0470.55,20291.15,417
NoThinkingBackbone=Qwen3-8B2026.0470.51,458——
Think or NotModel=Qwen3-4B2026.0469.86,59575.311,668
VanillaModel=DeepSeek-R12026.04667,5141007,514
RCPDModel=DeepSeek-R12026.04667,5181007,802
DEERModel=DeepSeek-R12026.0464.25,85573.26,292
CoDE-StopModel=DeepSeek-R12026.0463.85,54568.35,935
EATModel=DeepSeek-R12026.0462.56,43686.36,824
Answer ConvergenceModel=Nemotron-8B2026.0453.71,73629.92,399
Answer ConvergenceModel=Qwen3-4B2026.0451.12,05120.33,191
Answer ConvergenceModel=DeepSeek-R12026.04512,73433.14,170