Models · Compare
Tencent Hunyuan 2.0 Instruct vs Claude Opus 4.5
Rows highlighted in warm gray are where the models differ. Numbers carry their as-of date and primary source.
Specs
| Field | A: Tencent Hunyuan 2.0 Instruct | B: Claude Opus 4.5 |
|---|---|---|
| Released | 2025-12-05 | 2025-11-24 |
| Developer | Tencent | Anthropic |
| Openness | Open weights | Proprietary |
| License | Tencent Hunyuan Community License | Proprietary |
| OSI-approved | no | no |
| Data released | no | no |
| Training code | no | no |
| Architecture | moe | unknown |
| Total params | 406B | — |
| Active params | 32B | — |
| Experts | — | — |
| Context window | 256K | — |
| Attention | unknown | unknown |
| Position enc. | unknown | unknown |
| Pretraining tokens | — | — |
| Post-training | sft, rlhf | rlhf, constitutional |
| Training hardware | — | — |
| $/M input | — | $5.00 |
| $/M output | — | $25.00 |
| Output tok/sec | — | 51.8 |
Benchmarks
Missing scores render as not reported; never inferred. Bold highlights the leader per benchmark.
General reasoning
| MMLU-Pro | — | 88.9 2026-05-21 |
| GPQA-Diamond | — | 81.0 2026-05-21 |
Code
| LiveCodeBench | — | 73.8 2026-05-21 |
Math
| AIME 2025 | — | 62.7 2026-05-21 |
Context · A
Tencent's next-generation foundation model, released December 5 2025 as 406B total / 32B active MoE with a 256K context. Ships in HY 2.0 Think and HY 2.0 Instruct variants, integrated into Yuanbao and ima, and exposed via Tencent Cloud API. Reported sharp gains in math (IMO-AnswerBench) and coding (SWE-bench Verified) over predecessors.
Context · B
Anthropic's first Opus to cross 80 percent on SWE-Bench Verified per the lab's own numbers, released November 24 2025 at a two-thirds price cut versus Opus 4.1 ($5 / $25 per Mtok). Added an effort parameter for adjustable reasoning intensity, with medium-effort runs matching Sonnet 4.5 using 76 percent fewer output tokens.
Tencent Hunyuan 2.0 Instruct detail → · Claude Opus 4.5 detail →