Model card
Llama-PLLuM-8B-chat.
PLLuMopen-source
§ 01 · Benchmarks
Every benchmark Llama-PLLuM-8B-chat has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | Polish MT-Bench | Natural Language Processing · Polish Conversation Quality | humanities | 9.5% | #15 | — | source ↗ |
| 02 | Polish MT-Bench | Natural Language Processing · Polish Conversation Quality | reasoning | 5.3% | #26 | — | source ↗ |
| 03 | Polish MT-Bench | Natural Language Processing · Polish Conversation Quality | pl-score | 6.0% | #32 | — | source ↗ |
| 04 | Polish MT-Bench | Natural Language Processing · Polish Conversation Quality | writing | 7.2% | #34 | — | source ↗ |
| 05 | Polish MT-Bench | Natural Language Processing · Polish Conversation Quality | stem | 7.5% | #34 | — | source ↗ |
| 06 | Polish MT-Bench | Natural Language Processing · Polish Conversation Quality | extraction | 6.3% | #38 | — | source ↗ |
| 07 | Polish MT-Bench | Natural Language Processing · Polish Conversation Quality | roleplay | 6.2% | #38 | — | source ↗ |
| 08 | Polish MT-Bench | Natural Language Processing · Polish Conversation Quality | coding | 3.6% | #41 | — | source ↗ |
| 09 | Polish MT-Bench | Natural Language Processing · Polish Conversation Quality | math | 2.8% | #42 | — | source ↗ |
| 10 | PLCC | Natural Language Processing · Polish Cultural Competency | art-and-entertainment | 33.0% | #129 | — | source ↗ |
| 11 | PLCC | Natural Language Processing · Polish Cultural Competency | vocabulary | 35.0% | #135 | — | source ↗ |
| 12 | PLCC | Natural Language Processing · Polish Cultural Competency | geography | 46.0% | #135 | — | source ↗ |
| 13 | PLCC | Natural Language Processing · Polish Cultural Competency | culture-and-tradition | 34.0% | #138 | — | source ↗ |
| 14 | PLCC | Natural Language Processing · Polish Cultural Competency | history | 50.0% | #139 | — | source ↗ |
| 15 | PLCC | Natural Language Processing · Polish Cultural Competency | average | 38.5% | #142 | — | source ↗ |
| 16 | PLCC | Natural Language Processing · Polish Cultural Competency | grammar | 33.0% | #154 | — | 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 Llama-PLLuM-8B-chat actually performs.
§ 04 · Related models
Other PLLuM models scored on Codesota.
§ 05 · Sources & freshness
Where these numbers come from.
SpeakLeash/MT-Bench-PL
9
results
sdadas/PLCC
7
results
16 of 16 rows marked verified.