Spaces:

speakleash
/

polish_eq-bench

Running

djstrong commited on Dec 24, 2025

Commit

005e6be

verified ·

1 Parent(s): 85e3d78

Update benchmark_results.csv

Files changed (1) hide show

benchmark_results.csv CHANGED Viewed

@@ -190,4 +190,5 @@ Bielik-4.5B-v3.0-Instruct,2025-05-04 16:16:42,,speakleash/Bielik-4.5B-v3.0-Instr
 Bielik-11B-v2.6-Instruct,2025-05-30 15:56:57,,speakleash/Bielik-11B-v2.6-Instruct,,,74.13,eq-bench_v2_pl,170.0,1,transformers,,,
 pllum-12b-nc-instruct-250715,2025-07-18 13:33:16,,CYFRAGOVPL/pllum-12b-nc-instruct-250715,,,46.15,eq-bench_pl,129.0,1,transformers,,,129.0 questions were parseable (min is 83%)
 pllum-12b-nc-chat-250715/,2025-07-18 13:35:34,,CYFRAGOVPL/pllum-12b-nc-chat-250715,,,58.23,eq-bench_v2_pl,162.0,1,transformers,,,
-Bielik-11B-v3.0-Instruct,2025-12-21 14:47:06,,speakleash/Bielik-11B-v3.0-Instruct,,,71.2,eq-bench_v2_pl,171.0,1,transformers,,,

 Bielik-11B-v2.6-Instruct,2025-05-30 15:56:57,,speakleash/Bielik-11B-v2.6-Instruct,,,74.13,eq-bench_v2_pl,170.0,1,transformers,,,
 pllum-12b-nc-instruct-250715,2025-07-18 13:33:16,,CYFRAGOVPL/pllum-12b-nc-instruct-250715,,,46.15,eq-bench_pl,129.0,1,transformers,,,129.0 questions were parseable (min is 83%)
 pllum-12b-nc-chat-250715/,2025-07-18 13:35:34,,CYFRAGOVPL/pllum-12b-nc-chat-250715,,,58.23,eq-bench_v2_pl,162.0,1,transformers,,,
+Bielik-11B-v3.0-Instruct,2025-12-21 14:47:06,,speakleash/Bielik-11B-v3.0-Instruct,,,71.2,eq-bench_v2_pl,171.0,1,transformers,,,
+DeepSeek-V3-0324,2025-12-24 01:21:41,,deepseek-ai/DeepSeek-V3-0324,,,73.46,eq-bench_v2_pl,171.0,1,openai, ,,