Codesota · Models · Bielik-4.5B-v3.0-Instructspeakleash13 results · 3 benchmarks
Model card

Bielik-4.5B-v3.0-Instruct.

speakleashopen-source4.8B params
§ 01 · Benchmarks

Every benchmark Bielik-4.5B-v3.0-Instruct has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01CPTU-BenchNatural Language Processing · Polish Text Understandingphraseology3.7%#18/93source ↗
02CPTU-BenchNatural Language Processing · Polish Text Understandinglanguage-understanding3.6%#41/93source ↗
03CPTU-BenchNatural Language Processing · Polish Text Understandingaverage3.4%#44/93source ↗
04CPTU-BenchNatural Language Processing · Polish Text Understandingsentiment3.8%#44/93source ↗
05Polish EQ-BenchNatural Language Processing · Polish Emotional Intelligenceeq-score53.6%#50/101source ↗
06CPTU-BenchNatural Language Processing · Polish Text Understandingtricky-questions2.5%#55/93source ↗
07Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generaldyk66.5%#62/489source ↗
08Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalaverage56.1%#91/491source ↗
09Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalcbd32.4%#99/490source ↗
10Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalpolqa-open-book88.2%#102/489source ↗
11Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalbelebele83.8%#113/490source ↗
12Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalppc74.4%#131/490source ↗
13Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalpolemo2-in73.4%#203/490source ↗
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 02 · Strengths by area

Where Bielik-4.5B-v3.0-Instruct actually performs.

Natural Language Processing
3
benchmarks
avg rank #81.0
§ 04 · Related models

Other speakleash models scored on Codesota.

Bielik-1.5B-v1.0-DPO-001-L2
0 results
Bielik-1.5B-v1.0-DPO-001-L3
0 results
Bielik-1.5B-v1.0-DPO-001-L3-copy
0 results
Bielik-1.5B-v1.0-m3
0 results
Bielik-1.5B-v1.0-m3b
0 results
Bielik-1.5B-v1.0-m4
0 results
Bielik-1.5B-v3
0 results
Bielik-1.5B-v3.0-Instruct
1.6B params · 0 results
§ 05 · Sources & freshness

Where these numbers come from.

speakleash/open_pl_llm_leaderboard
7
results
SpeakLeash/CPTU-Bench
5
results
SpeakLeash/Polish-EQ-Bench
1
result
13 of 13 rows marked verified.