Qwen2.5-32B: benchmark scores, price and ranking

Qwen2.5-32B from Alibaba ranks #236 of 743 LLMs on the LLMs Tiger aggregate benchmark score (49.7), based on 2 benchmark results captured up to 2026-10-13.

Organisation: Alibaba
Type: Open-weight / local model
Open weights: Yes
Released: 2024-09-17 (source: epoch)
Aggregate rank: #236 of 743 (score 49.7)

Across the 2 benchmarks where at least ten models are scored, Qwen2.5-32B is in the top 10% on 0 and in the top half on 2.

Qwen2.5-32B benchmark results

Qwen2.5-32B benchmark scores, ranked against all models measured on each benchmark
Benchmark	Score	Rank	Source	Captured
MMLU-Pro	69.2%	#43 of 136	HuggingFace MMLU-Pro leaderboard	2026-10-13
Epoch ECI	129	#99 of 204	Epoch AI Benchmarking Hub	2026-10-13

About Qwen2.5-32B

Qwen2.5-32B is an open-weight model that can run on your own hardware from Alibaba. It was released on 2024-09-17, according to Epoch AI. No API price is listed for it yet. We hold 2 benchmark results for it across 2 areas, and none is in the top tenth of its board.

Where Qwen2.5-32B stands

On our aggregate score, Qwen2.5-32B is #236 of 743 ranked models, around the middle of the table. Its score is 49.7; the scale is centred on 50, so it sits 0.3 points below the typical model. That beats 68% of the ranked field. Among the 74 ranked Alibaba models it is #17. The next one up is Qwen2.5-72B at 50.1. The next one down is QwQ-32B at 49.7.

Qwen2.5-32B, benchmark by benchmark

MMLU-Pro puts Qwen2.5-32B at 69.2%, #43 of 136. That beats 68% of the models tested, but 18.9 points short of Darwin-180B-RSI (88.1%). The results either side are ERNIE-4.5-300B-A47B-Base-PT (69.5%) and mimo-v2.5-pro (68.5%). It covers 57-subject knowledge + reasoning. The board median is 55.3%, so Qwen2.5-32B is 14.0 points above it. Source: HuggingFace MMLU-Pro leaderboard, captured 2026-10-13.

On Epoch ECI, Qwen2.5-32B reaches 129. It ranks #99 of 204, ahead of 51% of the field, and 28 points behind Qwen 3.8 Max at 156. The results either side are Mistral Large 2 (Nov 2024) (129) and Mistral Large 2 (Jul 2024) (128). It covers Epoch Capabilities Index: Epoch's own aggregate of ~40 benchmarks. The board median is 127, so Qwen2.5-32B is 1 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

Strengths and weaknesses

Qwen2.5-32B has too few results on boards with ten or more models to say where it is strong or weak. Treat any single score as a data point, not a verdict.

Release history

The Alibaba model released before it was ollama/qwen2.5:32b on 2024-09-17, which scores 48.9. The next one was qwen2.5-32b-instruct on 2024-09-17, at 45.0.

Reading these numbers

The 2 scores on this page come from 2 sources: Epoch AI Benchmarking Hub (1), HuggingFace MMLU-Pro leaderboard (1). No official leaderboard supplied any of them, so treat them as third-party measurements. With 2 results the aggregate rank can move a lot when one new score arrives.

Models ranked nearby

#233 o3 (high) (49.8)
#234 ERNIE-4.5-300B-A47B-Base-PT (49.8)
#235 claude-haiku-4-5-20251001_1K (49.8)
#237 QwQ-32B (49.7)
#238 Devstral (2512) (49.7)
#239 claude-opus-4-1-20250805 (49.7)