Codesota · Models · Qwen3-4BQwen11 results · 1 benchmarks
Model card

Qwen3-4B.

Qwenopen-source
§ 02 · Benchmarks

Every benchmark Qwen3-4B has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalpolemo2-in85.7%#39/490—source ↗
02Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generaleq-bench51.3%#62/299—source ↗
03Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalpoquad-open-book68.8%#63/337—source ↗
04Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalklej-ner-mc53.2%#82/490—source ↗
05Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalklej-ner-generative53.6%#89/489—source ↗
06Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalaverage55.5%#96/491—source ↗
07Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalbelebele82.8%#123/490—source ↗
08Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalppc74.6%#125/490—source ↗
09Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generaldyk56.7%#132/489—source ↗
10Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalcbd25.6%#233/490—source ↗
11Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalpolqa-open-book78.3%#326/489—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 Qwen3-4B actually performs.

Natural Language Processing
1
benchmark
avg rank #124.5
§ 05 · Related models

Other Qwen models scored on Codesota.

Qwen/Qwen1.5-72B-Chat
72.3B params · 17 results
Qwen/Qwen2-72B-Instruct
72.7B params · 17 results
Qwen/Qwen2.5-1.5B-Instruct
1.54B params · 17 results
Qwen/Qwen2.5-14B-Instruct
14.8B params · 17 results
Qwen/Qwen2.5-32B-Instruct
32.8B params · 17 results
Qwen/Qwen2.5-3B-Instruct
3.09B params · 17 results
Qwen/Qwen2.5-72B-Instruct
72.7B params · 17 results
Qwen/Qwen2.5-7B-Instruct
7.62B params · 17 results
§ 06 · Sources & freshness

Where these numbers come from.

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