Add translategemma 12b Q4_E_H results, delete Q4_K_H and Q4_K_H results

Add HY-MT1.5-7B and HY-MT2-7B Q6_E_H MT results

Add gemma-4-26B-A4B-it-qat-q4_0-unquantized Q4_P_H vision result

Add gemma-4-26B-A4B-it-qat-q4_0-unquantized Q4_P_H math result

Add gemma-4-12B-it-qat-q4_0-unquantized math, vision, and audio results

Add GLM 4.7 Flash Q4_E_H math results

Add gemma-4-12B-it Q4_E_H math results

Add gemma-4-12B-it Q4_E_H vision results

Add gemma-4-12B-it Q4_E_H audio results

Add Qwen3-Omni-30B-A3B-Instruct Q4_K_H vision results

Add gemma-4-E4B-it chat results

Add Qwen3.5-27B Q4_K_H math results

correct vision table formatting

Add Qwen3.5-27B Q4_K_H vision results

Add Qwen3.5-9B Q4_K_H vision results

Add Qwen3.5-35B-A3B vision results

Add JoyAI-LLM-Flash Q4_K_H CHAT result

Add GLM-4.7-Flash Q4_P_H Math results

Add GLM-4.7-Flash Q4_P_H Math results

Add GLM-4.6V-Flash Q4_P_H Vision result

Add madlad400-10b-mt Q4_K_H MT result

Add HY-MT1.5-7B Q6_K_H MT result

Add translategemma-27b-it Q4_K_H MT result

Add translategemma-12b-it Q6_K_H MT result

Add translategemma-4b-it and translategemma-12b-it MT results

Add Deepseek-R1-Distill-Qwen-32B.Q4_K_H math result

Add madlad400-10b-mt MT results

Add MT category and plamo-2-translate.Q6_K_H results

Add Deepseek-R1-Distill-Qwen-14B.Q4_K_H math results.

Clarify benchmark methodology.

Add GLM-Z1-32B-0414 Q4_K_H math results

Add phi-4 Q4_K_H result in general model section

Refresh ultravox-v0_5-deepseek-r1-llama-3_1-8b result with new quant

Add refreshed ultravox llama3.1 8B results, add llama3.1 8B Q4_K_H result.

Add BBHA results to BBA, refresh Voxtral Mini 3B result

Add Ministral 3 3B Instruct 2512 Q4_K_H and Q6_K_H vision results

Add Ministral 3 8B Instruct 2512 vision result

Add GLM Z1 9B 0414 Q4_P_H partial result

Add Ministral-3-14B-Instruct-2512.Q4_K_H vision result

Add GLM Z1 9B 0414 Q4_K_H math partial results

Add Qwen3 VL 8B Instruct Q4_K_H vision result

fix vison version numbering error

Correct engine version for MiniCPM V Q6_K_H rerun.

Add MiniCPM-V-4_5 Q4_K_H vision result, rerun Q6_K_H vision result. Rerun LFM2-VL-1.6B vision result.

Add Q4_K_H and Q6_K_H quant results for Qwen 2.5 Omni 3B and VL 3B,

Add Q4_K_H quant results for Qwen 2.5 VL 7B and Qwen 2.5 Omni 7B

Update Qwen 2.5 VL 32B result

Correct engine version for Qwen3 VL 32B Instruct run

Add Qwen3 VL 32B Instruct Q4_K_H vision result

Add Qwen 2.5 Coder 14B Instruct Q4_K_H results