Rankings / Alibaba
Qwen2 5 32B Instruct
released 2024-09-17
BenchAtlas Index
as of 2026-07-14
base configuration
rank #403
8 families · 3 categories · medium
Benchmark evidence
11 results
coding
| LiveCodeBench v6 implementation=artificial-analysis | 24.8 % | independent | Artificial Analysis | |
| SciCode | 22.9 % | independent | Artificial Analysis |
external indices
| Intelligence Index v4.1 | 7.5 points | independent | Artificial Analysis |
knowledge science
| GPQA Diamond implementation=artificial-analysis | 46.6 % | independent | Artificial Analysis | |
| GPQA Diamond | 46.1 % | independent | Epoch AI Benchmarking Hub 2025-01-30 | |
| Humanity's Last Exam implementation=artificial-analysis | 3.8 % | independent | Artificial Analysis | |
| MMLU-Pro implementation=artificial-analysis | 69.7 % | independent | Artificial Analysis |
reasoning math
| AIME implementation=artificial-analysis | 11.0 % | independent | Artificial Analysis | |
| MATH-500 implementation=artificial-analysis | 80.5 % | independent | Artificial Analysis | |
| MATH Level 5 | 56.1 % | independent | Epoch AI Benchmarking Hub 2025-01-30 | |
| OTIS Mock AIME 2024–2025 | 7.4 % | independent | Epoch AI Benchmarking Hub 2025-02-25 |