AlibabaQwen2.5 32B Instruct
Qwen2.5 32B Instruct is an Alibaba open-weights model, released 17 Sept 2024. It is not yet ranked: 4 independent results so far, and the index needs at least five across two categories. Last measured 19 Sept 2024.stale: no new result in six months
- Blended price
- –
- Output speed
- –
- First answer
- –
- Context
- 128k
- Full answer
- –
- Cost per run
- –
- Released
- 17 Sept 2024
- Reasoning35
- Maths38
- Composite37
Benchmark results
See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | not stated | Source |
|---|---|---|
| GPQA Diamond | 46.1%#233 | Epoch AI Benchmarking Hub |
| GPQA Diamond (AA)not in index | 46.6%#446 | Artificial Analysis |
| Humanity's Last Exam (AA)not in index | 4.0%#552 | Artificial Analysis |
Maths
| Benchmark | not stated | Source |
|---|---|---|
| OTIS Mock AIME | 7.4%#237 | Epoch AI Benchmarking Hub |
| MATH Level 5 | 56.1%#50 | Epoch AI Benchmarking Hub |
Composite
| Benchmark | not stated | Source |
|---|---|---|
| AA Intelligence Index v4.3.2 | 6.9#504 | Artificial Analysis |
Safety & honesty
| Benchmark | not stated | Source |
|---|---|---|
| PropensityBenchnot in index | 22.9%#11 | Scale AI SEAL |
Price history
The price above, per 1M tokens, every day it changed.
More from Alibaba
See also
Questions people ask
- Why does Qwen2.5 32B Instruct have no BenchLeader Index score?
- The index needs at least five independent results across at least two categories; as of 25 Oct 2026 Qwen2.5 32B Instruct has 4 that count. Launch-post scores are never used, so it is ranked once independent publishers have measured it.
- When was Qwen2.5 32B Instruct released?
- Alibaba released Qwen2.5 32B Instruct on 17 Sept 2024.
Data as of 25 Oct 2026. Compare with another model.
Cite as: BenchLeader, “Qwen2.5 32B Instruct: benchmarks, pricing, speed and rank”, data as of 25 Oct 2026, https://www.benchleader.com/models/qwen2-5-32b.