Codesota · Models · gemma-3-4b-ptgoogle11 results · 1 benchmarks
Model card

gemma-3-4b-pt.

googleopen-source
§ 02 · Benchmarks

Every benchmark gemma-3-4b-pt has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalpoquad-open-book60.1%#186/337—source ↗
02Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalbelebele73.4%#196/490—source ↗
03Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generaleq-bench0.2%#295/299—source ↗
04Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalpolqa-open-book75.0%#356/489—source ↗
05Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalppc50.9%#401/490—source ↗
06Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalaverage20.7%#413/491—source ↗
07Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalklej-ner-mc26.6%#431/490—source ↗
08Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generaldyk28.9%#431/489—source ↗
09Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalcbd15.6%#438/490—source ↗
10Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalpolemo2-in52.8%#439/490—source ↗
11Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalklej-ner-generative28.3%#447/489—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 gemma-3-4b-pt actually performs.

Natural Language Processing
1
benchmark
avg rank #366.6
§ 05 · Related models

Other google models scored on Codesota.

gemma-1.1-2b-it
0 results
gemma-2-27b-it
0 results
gemma-2-9b-it
0 results
gemma-3-12b-it
0 results
gemma-3-12b-pt
0 results
gemma-3-1b-it
0 results
gemma-3-1b-pt
0 results
gemma-3-27b-pt
0 results
§ 06 · Sources & freshness

Where these numbers come from.

speakleash/open_pl_llm_leaderboard
11
results
11 of 11 rows marked verified.