Model comparison
Hunyuan Hy3 vs Claude Mythos 5
- Input
- ¥1.00
- Output
- ¥4.00
- Context
- 256K
- Released
- 2026-07-06
- Input
- $10 / 1M tokens
- Output
- $50 / 1M tokens
- Context
- 1M
- Released
- 2026-06-09
Claude Mythos 5 scores higher on 2 of the 2 benchmarks both models report; Claude Mythos 5 has the larger context window (1M vs 256K); Hunyuan Hy3 ships open weights while Claude Mythos 5 is API-only.
Specs and pricing side by side
| Spec | Hunyuan Hy3 | Claude Mythos 5 |
|---|---|---|
| Maker | Tencent | Anthropic |
| Released | 2026-07-06 | 2026-06-09 |
| Context window | 256K | 1M |
| Max output | not published | 128K tokens |
| Input price | ¥1.00 | $10 / 1M tokens |
| Output price | ¥4.00 | $50 / 1M tokens |
| Parameters | 295B total · 21B active | Undisclosed |
| License | Apache-2.0 | Proprietary |
| Weights | Open weights | API only |
| Modalities | Text | Text, Vision, PDF |
| Knowledge cutoff | not published | January 2026 |
Benchmarks both models report
| Benchmark | Hunyuan Hy3 | Claude Mythos 5 |
|---|---|---|
| SWE-Bench Verified | 78% | 95% |
| SWE-Bench Pro | 57.9% | 80.3% |
Scores are as published by each maker or its cited source; harness, reasoning effort and date can differ between rows, so treat small gaps as ties. Sources are listed on each model page.
Which one should you pick?
Pick Hunyuan Hy3 if…
- You want to self-host or fine-tune (open weights, Apache-2.0).
- Your use case is: self-hosted agentic coding, tool use and terminal automation via vLLM or SGLang recipes.
Pick Claude Mythos 5 if…
- You care about SWE-Bench Verified, SWE-Bench Pro (it scores higher on 2 shared benchmarks).
- You need the longer context (1M vs 256K).
- You need Vision / PDF input, which Hunyuan Hy3 lacks.
- Your use case is: defensive cybersecurity: finding and analyzing software vulnerabilities across large codebases (Project Glasswing partners).
FAQ
Which is better, Hunyuan Hy3 or Claude Mythos 5?
Claude Mythos 5 scores higher on 2 of the 2 benchmarks both models report; Claude Mythos 5 has the larger context window (1M vs 256K); Hunyuan Hy3 ships open weights while Claude Mythos 5 is API-only. The better pick depends on whether you value benchmark scores, price per token, context length or openness for your workload.
What are the context windows of Hunyuan Hy3 and Claude Mythos 5?
Hunyuan Hy3 offers 256K; Claude Mythos 5 offers 1M with up to 128K tokens output.
Is Hunyuan Hy3 newer than Claude Mythos 5?
Hunyuan Hy3 was released 2026-07-06; Claude Mythos 5 was released 2026-06-09.