Rankings / Alibaba
Qwen3 5 Plus
released 2026-02-16
BenchAtlas Index
as of 2026-09-11
thinking
rank #161
7 families · 3 categories · medium
Benchmark evidence
18 results
external indices
| ECI | no reasoning | 146.8 points | independent | Epoch AI Benchmarking Hub |
| ECI | 146.8 points | independent | Epoch AI Benchmarking Hub |
factuality
| SimpleQA Verified | 26.0 % | independent | Epoch AI Benchmarking Hub 2026-05-13 | |
| SimpleQA Verified | 25.4 % | independent | Epoch AI Benchmarking Hub 2026-08-27 |
knowledge science
| GPQA Diamond implementation=vals-ai | thinking | 87.4 % | independent | Vals AI |
| GPQA Diamond | 84.8 % | independent | Epoch AI Benchmarking Hub 2026-08-07 | |
| GPQA Diamond | 84.2 % | independent | Epoch AI Benchmarking Hub 2026-05-13 | |
| MMLU-Pro implementation=vals-ai | thinking | 87.2 % | independent | Vals AI |
multimodal
| MMMU implementation=vals-ai | thinking | 22.8 % | independent | Vals AI |
professional
| CaseLaw | thinking | 59.7 % | independent | Vals AI |
| CorpFin | thinking | 65.3 % | independent | Vals AI |
| LegalBench | thinking | 85.1 % | independent | Vals AI |
| MedQA | thinking | 95.2 % | independent | Vals AI |
reasoning math
| AIME implementation=vals-ai | thinking | 86.0 % | independent | Vals AI |
| FrontierMath | 21.0 % | independent | Epoch AI Benchmarking Hub 2026-05-14 | |
| FrontierMath Tier 4older version | 2.1 % | independent | Epoch AI Benchmarking Hub 2026-05-15 | |
| OTIS Mock AIME 2024–2025 | 86.7 % | independent | Epoch AI Benchmarking Hub 2026-08-07 | |
| OTIS Mock AIME 2024–2025 | 85.0 % | independent | Epoch AI Benchmarking Hub 2026-05-14 |