Model card
Bielik-1.5B-v3.0-Instruct.
speakleashopen-source1.6B params
§ 01 · Benchmarks
Every benchmark Bielik-1.5B-v3.0-Instruct has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | CPTU-Bench | Natural Language Processing · Polish Text Understanding | sentiment | 3.5% | #59 | — | source ↗ |
| 02 | CPTU-Bench | Natural Language Processing · Polish Text Understanding | average | 2.4% | #78 | — | source ↗ |
| 03 | CPTU-Bench | Natural Language Processing · Polish Text Understanding | tricky-questions | 1.2% | #79 | — | source ↗ |
| 04 | CPTU-Bench | Natural Language Processing · Polish Text Understanding | phraseology | 2.4% | #81 | — | source ↗ |
| 05 | CPTU-Bench | Natural Language Processing · Polish Text Understanding | language-understanding | 2.3% | #83 | — | source ↗ |
| 06 | Open PL LLM Leaderboard | Natural Language Processing · Polish LLM General | average | 41.4% | #190 | — | source ↗ |
| 07 | Open PL LLM Leaderboard | Natural Language Processing · Polish LLM General | ppc | 69.8% | #222 | — | source ↗ |
| 08 | Open PL LLM Leaderboard | Natural Language Processing · Polish LLM General | belebele | 71.0% | #233 | — | source ↗ |
| 09 | Open PL LLM Leaderboard | Natural Language Processing · Polish LLM General | polqa-open-book | 83.3% | #235 | — | source ↗ |
| 10 | Open PL LLM Leaderboard | Natural Language Processing · Polish LLM General | polemo2-in | 69.8% | #319 | — | source ↗ |
| 11 | Open PL LLM Leaderboard | Natural Language Processing · Polish LLM General | cbd | 20.0% | #325 | — | source ↗ |
| 12 | Open PL LLM Leaderboard | Natural Language Processing · Polish LLM General | dyk | 40.1% | #345 | — | source ↗ |
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-1.5B-v3.0-Instruct actually performs.
§ 04 · Related models
Other speakleash models scored on Codesota.
§ 05 · Sources & freshness
Where these numbers come from.
speakleash/open_pl_llm_leaderboard
7
results
SpeakLeash/CPTU-Bench
5
results
12 of 12 rows marked verified.