Codesota · Models · 🚧mistral_7B-v2/spkl-only_sft_v2/e1_base/spkl-only_7e6w-e3_78cf3243speakleash9 results · 1 benchmarks
Model card
🚧mistral_7B-v2/spkl-only_sft_v2/e1_base/spkl-only_7e6w-e3_78cf3243.
speakleashopen-source
§ 02 · Benchmarks
Every benchmark 🚧mistral_7B-v2/spkl-only_sft_v2/e1_base/spkl-only_7e6w-e3_78cf3243 has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | Open PL LLM Leaderboard | Natural Language Processing · Polish LLM General | polqa-open-book | 85.0% | #202 | — | source ↗ |
| 02 | Open PL LLM Leaderboard | Natural Language Processing · Polish LLM General | cbd | 26.6% | #213 | — | source ↗ |
| 03 | Open PL LLM Leaderboard | Natural Language Processing · Polish LLM General | polemo2-in | 71.2% | #270 | — | source ↗ |
| 04 | Open PL LLM Leaderboard | Natural Language Processing · Polish LLM General | klej-ner-mc | 38.3% | #288 | — | source ↗ |
| 05 | Open PL LLM Leaderboard | Natural Language Processing · Polish LLM General | ppc | 62.8% | #314 | — | source ↗ |
| 06 | Open PL LLM Leaderboard | Natural Language Processing · Polish LLM General | belebele | 64.1% | #356 | — | source ↗ |
| 07 | Open PL LLM Leaderboard | Natural Language Processing · Polish LLM General | average | 26.9% | #379 | — | source ↗ |
| 08 | Open PL LLM Leaderboard | Natural Language Processing · Polish LLM General | klej-ner-generative | 36.0% | #380 | — | source ↗ |
| 09 | Open PL LLM Leaderboard | Natural Language Processing · Polish LLM General | dyk | 37.5% | #380 | — | 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.
§ 03 · Strengths by area
Where 🚧mistral_7B-v2/spkl-only_sft_v2/e1_base/spkl-only_7e6w-e3_78cf3243 actually performs.
§ 05 · Related models
Other speakleash models scored on Codesota.
§ 06 · Sources & freshness
Where these numbers come from.
speakleash/open_pl_llm_leaderboard
9
results
9 of 9 rows marked verified.