RWT
8.0 score
LLM Leaderboard · Open Weight
Hy3 benchmarks — leaderboard rank, pricing, and comparisons.
Hy3 ranks #39 on the AskClash LLM leaderboard with an overall score of 51.5. It scores 78.0 on SWE-bench and 71.7 on Terminal-Bench. Compare Hy3 vs GPT, Claude, Gemini, DeepSeek, open-weight, and frontier AI models using public benchmark scores, token pricing, context window, and access details.
Rank #39AskClash overall score: 51.5
$0.12 / $0.43Input and output token price, when published. Context: 256K.
Visit websiteVisit the model provider's website.
Hy3 benchmark snapshot
AskClash combines public LLM benchmark cells into a weighted percentile score and penalizes missing coverage so narrow rows do not dominate better-measured models.
Overall51.5
Benchmark cells9
Context256K
CreatorTencent
Hy3 public benchmark scores
Cached benchmark values can include HLE, GPQA, SWE-bench, SWE-Pro, SWE-Atlas, Terminal-Bench, MCP Atlas, MMMU-Pro, ARC-AGI-2, Tau2, and model-specific coding or agent scores.
HLE
53.2 score
GPQA
90.4 score
SWE-bench
78.0 score
SWE-Pro
57.9 score
Terminal-Bench
71.7 score
GDPval-AA
1067.3 score
MCP Atlas
79.1 score
Tau2
92.7 score
MRCR
75.1 score
Hy3 vs other AI models
Use these comparison links to evaluate Hy3 against nearby LLMs by benchmark score, price, context window, and provider.
Related AI and tech coverage
Cached AskClash article matches that can provide release, provider, benchmark, pricing, or market context around this model.
SGLang — RadixAttention Inference Server v0.5.15 Release Notes
**New Model Support**: [Hunyuan 3 (Hy3)](https://docs.sglang.io/cookbook/autoregressive/Tencent/Hy3), Hierarchical Reasoning Model (HRM-Text), NVIDIA LocateAnything-3B, [Baidu Unlimited-OCR](https://docs.sglang.io/cookbook/autoregressive/Baidu/Unlimited-OCR),
Last cached leaderboard date: July 6, 2026. This model page is generated from the AskClash LLM Leaderboard cache and linked from the live leaderboard.