Expired50% confidenceBenchmarkExact time
Tencent's own internal test data claims that Hunyuan V3 surpasses DeepSeek-V4-Pro in almost every domain, with only slight underperformance on MCP-related test items.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/10/2026
First Seen
Valid until: 10/8/2026(expired)
Sources
Related Claims
UnverifiedPhi-3-mini（3.8B参数）在部分基准测试上超越了Mixtral 8x7B等更大的混合专家模型66% similarUnverifiedKimi K3's 2.8 trillion parameter scale surpasses the previously largest open-weight model, DeepSeek-V3, which had 671 billion parameters.65% similarUnverifiedGLM-4.7 surpasses DeepSeek V3.2 and Claude Sonnet 4.5 in code capability benchmarks.65% similarUnverifiedQwen3-4B is already on par with DeepSeek V3 or GPT-4o on multiple reasoning evaluation metrics.65% similarUnverifiedAt the time of its release, DeepSeek-V3 matched or surpassed Claude 3.5 Sonnet on multiple benchmarks, with training costs reportedly a fraction of those of mainstream closed-source models.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/465611API
curl https://kongchang.com/api/v1/knowledge/claims/465611MCP
get_claim(id=465611)