List your company

Objective Performance Evaluation on Objective Benchmarks

63.2Average Performance ScoreEBD
8.70422.8523751.148May 27, 2026

Evaluation results

MethodLinks
EBDBackbone=Qwen3-8B-Base2026.0563.241.479.268.9
Power SamplingBackbone=Qwen3-8B-Base2026.0562.240.979.266.5
EBDBackbone=Qwen2.5-7B2026.0555.732.87262.2
DirectBackbone=Qwen3-8B-Base2026.0554.434.36959.8
EBDBackbone=Olmo-7B2026.0553.834.370.456.7
Power SamplingBackbone=Qwen2.5-7B2026.0551.330.366.457.3
DirectBackbone=Qwen2.5-7B2026.0539.822.255.841.5
Power SamplingBackbone=Olmo-7B2026.0538.226.846.441.5
DirectBackbone=Olmo-7B2026.0532.930.336.631.7
EBDBackbone=Llama3-8B2026.0526.223.74.250.6
Power SamplingBackbone=Llama3-8B2026.0519.515.70.842.1
EBDBackbone=Mistral-7B2026.0516.824.13.223.2
DirectBackbone=Llama3-8B2026.0515.515.21.629.9
Power SamplingBackbone=Mistral-7B2026.0512.618.20.618.9
DirectBackbone=Mistral-7B2026.0510.816.7114.7