Alibaba (Qwen)
Qwen1.5-72B benchmark results
8 results on 6 benchmarks from 5 sources.
Open weights Released: Feb 4, 2024 Updated Oct 22, 2026
Also listed as: qwen1.5-72b-chat · Qwen1.5 (72B) · Qwen1.5-72B-Chat
All benchmark results
| Benchmarks | Score | Rank | Setting | Source type | Date |
|---|---|---|---|---|---|
| LMArena Text | 1234 | 328 | Overall, style control on; 39302 votes; 95% CI 1228–1239“qwen1.5-72b-chat” | Official leaderboard | Oct 8, 2026 |
| GPQA Diamond | 28.8% | 263 | Epoch AI run, accuracy | Independent run | Jan 27, 2025 |
| MMLU | 77.4% | 32 | Exact match; 5-shot“Qwen1.5 (72B)” | Official leaderboard via Epoch AI | — |
| MMLU-Pro | 52.6% | 159 | Overall accuracy; data source: TIGER-Lab; 72B“Qwen1.5-72B-Chat” | Official leaderboard | Mar 11, 2026 |
| HumanEval / HumanEval+ | 68.3% | 48 | HumanEval (base tests), pass@1 greedy“Qwen1.5-72B-Chat” | Official leaderboard | Dec 26, 2024 |
| HumanEval / HumanEval+ | 59.1% | 52 | HumanEval+ (extended tests), pass@1 greedy“Qwen1.5-72B-Chat” | Official leaderboard | Dec 26, 2024 |
| CMMLU | 83.5% | 10 | Five-shot average | Official leaderboard | Dec 6, 2024 |
| CMMLU | 81.8% | 8 | Zero-shot average | Official leaderboard | Dec 6, 2024 |
FAQ
Where do these Qwen1.5-72B scores come from?
From CMMLU leaderboard (GitHub README), Epoch AI Benchmarking Hub, EvalPlus leaderboard, LMArena leaderboard dataset, and MMLU-Pro leaderboard (TIGER-Lab). Each row links to the original leaderboard, dataset or report, and vendor-reported numbers are labelled.