Codesota · Models · WizardLM-2-8x22Balpindale14 results · 3 benchmarks
Model card

WizardLM-2-8x22B.

alpindaleopen-source141B params
§ 01 · Benchmarks

Every benchmark WizardLM-2-8x22B has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01CPTU-BenchNatural Language Processing · Polish Text Understandingphraseology4.2%#4/93source ↗
02Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generaleq-bench62.8%#13/299source ↗
03Polish EQ-BenchNatural Language Processing · Polish Emotional Intelligenceeq-score69.6%#21/101source ↗
04CPTU-BenchNatural Language Processing · Polish Text Understandingaverage3.7%#28/93source ↗
05CPTU-BenchNatural Language Processing · Polish Text Understandinglanguage-understanding3.8%#32/93source ↗
06Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalbelebele89.1%#35/490source ↗
07CPTU-BenchNatural Language Processing · Polish Text Understandingtricky-questions3.1%#41/93source ↗
08CPTU-BenchNatural Language Processing · Polish Text Understandingsentiment3.7%#53/93source ↗
09Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalaverage62.4%#56/491source ↗
10Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generaldyk67.1%#58/489source ↗
11Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalpolqa-open-book89.5%#67/489source ↗
12Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalcbd33.1%#87/490source ↗
13Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalppc76.5%#90/490source ↗
14Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalpolemo2-in77.4%#135/490source ↗
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 WizardLM-2-8x22B actually performs.

Natural Language Processing
3
benchmarks
avg rank #51.4
§ 04 · Related models

Other alpindale models scored on Codesota.

Mistral-7B-v0.2-hf
0 results
§ 05 · Sources & freshness

Where these numbers come from.

speakleash/open_pl_llm_leaderboard
8
results
SpeakLeash/CPTU-Bench
5
results
SpeakLeash/Polish-EQ-Bench
1
result
14 of 14 rows marked verified.