Model card
Qwen3-4B.
Qwenopen-source
§ 01 · Benchmarks
Every benchmark Qwen3-4B has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | Open PL LLM Leaderboard | Natural Language Processing · Polish LLM General | polemo2-in | 85.7% | #39 | — | source ↗ |
| 02 | Open PL LLM Leaderboard | Natural Language Processing · Polish LLM General | eq-bench | 51.3% | #62 | — | source ↗ |
| 03 | Open PL LLM Leaderboard | Natural Language Processing · Polish LLM General | average | 55.5% | #96 | — | source ↗ |
| 04 | Open PL LLM Leaderboard | Natural Language Processing · Polish LLM General | belebele | 82.8% | #123 | — | source ↗ |
| 05 | Open PL LLM Leaderboard | Natural Language Processing · Polish LLM General | ppc | 74.6% | #125 | — | source ↗ |
| 06 | Open PL LLM Leaderboard | Natural Language Processing · Polish LLM General | dyk | 56.7% | #132 | — | source ↗ |
| 07 | Open PL LLM Leaderboard | Natural Language Processing · Polish LLM General | cbd | 25.6% | #233 | — | source ↗ |
| 08 | Open PL LLM Leaderboard | Natural Language Processing · Polish LLM General | polqa-open-book | 78.3% | #326 | — | 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.
§ 02 · Strengths by area
Where Qwen3-4B actually performs.
§ 04 · Related models
Other Qwen models scored on Codesota.
QwQ-32B
0 results
QwQ-32B-Preview
0 results
Qwen/Qwen2.5-0.5B-Instruct
0.49B params · 0 results
Qwen/Qwen3-14B non-thinking (API)
14B params · 0 results
Qwen/Qwen3-235B-A22B non-thinking (API)
235B params · 0 results
Qwen/Qwen3-30B-A3B non-thinking (API)
30B params · 0 results
Qwen/Qwen3-32B non-thinking (API)
32B params · 0 results
Qwen/Qwen3-8B non-thinking (API)
8B params · 0 results
§ 05 · Sources & freshness
Where these numbers come from.
speakleash/open_pl_llm_leaderboard
8
results
8 of 8 rows marked verified.