Codesota · Models · Qwen/Qwen2.5-72B-InstructQwen17 results · 3 benchmarks
Model card

Qwen/Qwen2.5-72B-Instruct.

Qwenopen-weights72.7B params
§ 02 · Benchmarks

Every benchmark Qwen/Qwen2.5-72B-Instruct has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generaldyk78.0%#1/489source ↗
02Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalbelebele93.0%#2/490source ↗
03Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generaleq-bench64.3%#2/299source ↗
04Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalppc81.8%#4/490source ↗
05Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalaverage67.9%#4/491source ↗
06Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalklej-ner-mc61.0%#11/490source ↗
07CPTU-BenchNatural Language Processing · Polish Text Understandingaverage3.9%#14/93source ↗
08CPTU-BenchNatural Language Processing · Polish Text Understandingphraseology3.9%#14/93source ↗
09Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalpoquad-open-book72.4%#14/337source ↗
10CPTU-BenchNatural Language Processing · Polish Text Understandingtricky-questions3.8%#15/93source ↗
11CPTU-BenchNatural Language Processing · Polish Text Understandinglanguage-understanding4.0%#17/93source ↗
12Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalklej-ner-generative59.2%#17/489source ↗
13Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalpolemo2-in86.6%#17/490source ↗
14Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalcbd38.1%#19/490source ↗
15CPTU-BenchNatural Language Processing · Polish Text Understandingsentiment4.1%#25/93source ↗
16Polish EQ-BenchNatural Language Processing · Polish Emotional Intelligenceeq-score68.5%#25/101source ↗
17Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalpolqa-open-book83.6%#229/489source ↗
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 Qwen/Qwen2.5-72B-Instruct actually performs.

Natural Language Processing
3
benchmarks
avg rank #25.3
§ 05 · Related models

Other Qwen models scored on Codesota.

Qwen3-VL-235B-A22B-Instruct
7 results · 1 SOTA
Qwen3-VL-235B-A22B-Thinking
7 results
Qwen3-VL-8B-Instruct
7 results
Qwen3-Coder-Next
5 results
QwQ-32B
0 results
QwQ-32B-Preview
0 results
Qwen-3.7-Max
0 results
Qwen/Qwen1.5-72B-Chat
72.3B params · 0 results
§ 06 · Sources & freshness

Where these numbers come from.

speakleash/open_pl_llm_leaderboard
11
results
SpeakLeash/CPTU-Bench
5
results
SpeakLeash/Polish-EQ-Bench
1
result
17 of 17 rows marked verified.