List your company

Large Language Model Evaluation on Open LLM Leaderboard v1 (test)

69.6Average ScoreFP16
49.195254.492659.7965.0874Dec 30, 2025Jan 21, 2026Feb 12, 2026Mar 6, 2026Mar 28, 2026Apr 19, 2026May 11, 2026

Evaluation results

MethodLinks
FP16Q Config=FP162026.0169.655.658.159.774.970.188.810080.2
Bielik-11B-v3Model Type=Base2025.1268.4561.4381.3847.6567.5578.5374.15——
Qwen1.5-14BModel Type=Base2025.1266.756.5781.0852.0669.3673.4867.63——
TPAW Iter-3Model=Llama3.1-8B2026.0566.1465.5480.7754.4664.5676.3255.19——
LoPRo.vQ Config=W3A162026.0166.155.354.954.971.769.680.994.9175.1
Bielik-11B-v2Model Type=Base2025.1265.8760.5879.8446.1363.0677.8267.78——
Qwen-14BModel Type=Base2025.1265.8658.2883.9949.4367.776.858.98——
TPAW Iter-4Model=Llama3.1-8B2026.0565.7763.2380.9154.4464.4676.2455.34——
LoPRoQ Config=W3A162026.0165.754.353.954.271.169.981.294.475.3
TPAW Iter-2Model=Llama3.1-8B2026.0565.6462.9780.6354.1164.4576.1655.5——
TPAW Iter-1Model=Llama3.1-8B2026.0565.4462.8880.6653.7164.2975.9355.19——
SPIN Iter-4Model=Llama3.1-8B2026.0564.8862.0380.7853.9263.9776.0152.54——
SPIN Iter-1Model=Llama3.1-8B2026.0564.8261.6980.4453.6263.9475.353.9——
SPIN Iter-3Model=Llama3.1-8B2026.0564.862.280.7453.9864.1576.0151.71——
DPOModel=Llama3.1-8B2026.0564.7963.1480.4657.4263.0874.3550.27——
SPIN Iter-2Model=Llama3.1-8B2026.0564.7362.0380.6353.8163.9775.6152.31——
SFTModel=Llama3.1-8B2026.0563.9360.7579.4851.6563.7274.8253.15——
Meta-Llama-3-8BModel Type=Base2025.1262.6260.2482.2342.9366.778.4545.19——
Bielik-4.5B-v3Model Type=Base2025.1261.0251.1973.0145.6361.3271.3563.61——
Mistral-7B-v0.1Model Type=Base2025.1260.9759.9883.3142.1564.1678.3737.83——
Mistral-7B-v0.2Model Type=Base2025.1260.3760.8483.0841.7663.6278.2234.72——
DPOModel=Qwen2.5-1.5B2026.0558.5554.5266.2949.3959.4164.9656.71——
TPAW Iter-4Model=Qwen2.5-1.5B2026.0557.7652.5666.347.959.6465.1155.04——
TPAW Iter-3Model=Qwen2.5-1.5B2026.0557.6553.6766.1847.9159.5265.0453.6——
SPIN Iter-4Model=Qwen2.5-1.5B2026.0557.6153.5866.0548.4159.5864.7253.3——
SPIN Iter-3Model=Qwen2.5-1.5B2026.0557.4752.6566.2548.3859.5664.4853.53——
TPAW Iter-2Model=Qwen2.5-1.5B2026.0557.3853.4166.0847.9159.5864.1753.15——
TPAW Iter-1Model=Qwen2.5-1.5B2026.0557.2752.9965.7747.6459.564.9652.77——
SPIN Iter-2Model=Qwen2.5-1.5B2026.0557.2652.056648.2559.4364.453.45——
SPIN Iter-1Model=Qwen2.5-1.5B2026.0557.1351.7965.7647.8259.2664.3353.83——
SFTModel=Qwen2.5-1.5B2026.0556.2850.9464.9146.8358.9364.851.25——
LoPRo.vQ Config=W2A162026.0155.647.947.242.761.866.255.579.8967.9
LoPRoQ Config=W2A162026.0151.440.644.340.255.764.452.373.8962.5
Bielik-7B-v0.1Model Type=Base2025.1249.9845.2267.9247.1643.266.8529.49——