Codesota · Models · berkeley-nest/Starling-LM-7B-alphaberkeley-nest18 results · 3 benchmarks
Model card

berkeley-nest/Starling-LM-7B-alpha.

berkeley-nestopen-weights7.24B params
§ 02 · Benchmarks

Every benchmark berkeley-nest/Starling-LM-7B-alpha has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalpoleval2018-task31438.04#18/56—source ↗
02Polish EQ-BenchNatural Language Processing · Polish Emotional Intelligenceeq-score49.6%#55/101—source ↗
03CPTU-BenchNatural Language Processing · Polish Text Understandingphraseology2.9%#66/93—source ↗
04CPTU-BenchNatural Language Processing · Polish Text Understandinglanguage-understanding2.9%#73/93—source ↗
05CPTU-BenchNatural Language Processing · Polish Text Understandingtricky-questions1.7%#74/93—source ↗
06CPTU-BenchNatural Language Processing · Polish Text Understandingaverage2.6%#75/93—source ↗
07CPTU-BenchNatural Language Processing · Polish Text Understandingsentiment3.1%#79/93—source ↗
08Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalklej-ner-generative51.4%#100/489—source ↗
09Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalklej-ner-mc51.4%#102/490—source ↗
10Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generaldyk61.1%#106/489—source ↗
11Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generaleq-bench36.7%#112/299—source ↗
12Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalpolemo2-in79.0%#114/490—source ↗
13Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalcbd31.1%#122/490—source ↗
14Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalaverage50.0%#134/491—source ↗
15Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalpoquad-open-book63.2%#135/337—source ↗
16Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalbelebele77.2%#161/490—source ↗
17Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalppc60.9%#335/490—source ↗
18Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalpolqa-open-book76.9%#336/489—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 berkeley-nest/Starling-LM-7B-alpha actually performs.

Natural Language Processing
3
benchmarks
avg rank #122.1
§ 06 · Sources & freshness

Where these numbers come from.

speakleash/open_pl_llm_leaderboard
12
results
SpeakLeash/CPTU-Bench
5
results
SpeakLeash/Polish-EQ-Bench
1
result
18 of 18 rows marked verified.