Codesota · Models · Qwen2.5-3B-InstructAlibaba9 results · 1 benchmarks
Model card

Qwen2.5-3B-Instruct.

Alibabaopen-source
§ 01 · Benchmarks

Every benchmark Qwen2.5-3B-Instruct has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01Polish MT-BenchNatural Language Processing · Polish Conversation Qualitymath6.4%#19/50—source ↗
02Polish MT-BenchNatural Language Processing · Polish Conversation Qualityextraction8.4%#22/50—source ↗
03Polish MT-BenchNatural Language Processing · Polish Conversation Qualitycoding5.0%#26/50—source ↗
04Polish MT-BenchNatural Language Processing · Polish Conversation Qualitypl-score6.3%#29/50—source ↗
05Polish MT-BenchNatural Language Processing · Polish Conversation Qualityreasoning4.3%#34/50—source ↗
06Polish MT-BenchNatural Language Processing · Polish Conversation Qualityroleplay6.5%#35/50—source ↗
07Polish MT-BenchNatural Language Processing · Polish Conversation Qualityhumanities7.8%#40/50—source ↗
08Polish MT-BenchNatural Language Processing · Polish Conversation Qualitywriting5.5%#40/50—source ↗
09Polish MT-BenchNatural Language Processing · Polish Conversation Qualitystem6.8%#41/50—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 Qwen2.5-3B-Instruct actually performs.

Natural Language Processing
1
benchmark
avg rank #31.8
§ 04 · Related models

Other Alibaba models scored on Codesota.

Qwen2-VL 72B
4 results
Qwen2.5-72B-Instruct
72B params · 4 results
Qwen2.5-Coder 32B
32B params · 4 results
GOT-OCR2.0
3 results
Qwen 3 72B
72B params · 2 results
Qwen2.5-VL 32B
2 results
Qwen2.5-VL 72B
72B params · 2 results
Qwen 3 14B
14B params · 1 result
§ 05 · Sources & freshness

Where these numbers come from.

SpeakLeash/MT-Bench-PL
9
results
9 of 9 rows marked verified.