Models · Compare
Qwen 2 72B Instruct vs Claude 3.5 Sonnet
Rows highlighted in warm gray are where the models differ. Numbers carry their as-of date and primary source.
Specs
| Field | A: Qwen 2 72B Instruct | B: Claude 3.5 Sonnet |
|---|---|---|
| Released | 2024-06-06 | 2024-06-20 |
| Developer | Alibaba | Anthropic |
| Openness | Source-available | Proprietary |
| License | Tongyi Qianwen License | Proprietary |
| OSI-approved | no | no |
| Data released | no | no |
| Training code | no | no |
| Architecture | dense | unknown |
| Total params | 72.7B | — |
| Active params | — | — |
| Experts | — | — |
| Context window | 131K | 200K |
| Attention | gqa | unknown |
| Position enc. | rope | unknown |
| Pretraining tokens | — | — |
| Post-training | sft, rlhf, dpo | rlhf, constitutional |
| Training hardware | — | — |
| $/M input | $0.00 | — |
| $/M output | $0.00 | — |
| Output tok/sec | 0 | — |
Benchmarks
Missing scores render as not reported; never inferred. Bold highlights the leader per benchmark.
General reasoning
| MMLU | 82.3 2024-06-07 | — |
| MMLU-Pro | 64.4 2024-06-07 | — |
| GPQA-Diamond | 37.1 2026-05-21 | — |
Code
| HumanEval | 86.0 2024-06-07 | — |
| LiveCodeBench | 15.9 2026-05-21 | — |
Math
| MATH | 59.7 2024-06-07 | — |
| AIME 2024 | 14.7 2026-05-21 | — |
Held-out / arena
| IFEval | 77.6 2024-06-07 | — |
Context · A
Predecessor to the Qwen 2.5 family. The 72B class brought 128K-token context via YaRN and added 27 multilingual languages to the pretraining mix, but Alibaba kept the 72B variant under the Tongyi Qianwen License while smaller siblings moved to Apache 2.0.
Context · B
The first Claude release to beat its own larger sibling (Claude 3 Opus) on most benchmarks. Established Artifacts, driving a wave of code-and-canvas product copies.