HLE
25.5 score
LLM Leaderboard · Open Weight
Hy3 Preview benchmarks, pricing, and LLM comparison.
Compare Hy3 Preview vs GPT, Claude, Gemini, DeepSeek, open-weight, and frontier AI models using public benchmark scores, token pricing, context window, and access details.
Rank #31AskClash overall score: 20.2
$0 / $0Input and output token price, when published. Context: 256K.
APIBilling and access path cached for this model row.
Hy3 Preview 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.
Overall20.2
Benchmark cells6
Context256K
CreatorTencent
Hy3 Preview 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.
GPQA
87.2 score
IFEval
63.1 score
SWE-bench
74.4 score
Terminal-Bench
54.4 score
Tau2
92.7 score
Hy3 Preview vs other AI models
Use these comparison links to evaluate Hy3 Preview 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.
Sources: the early Chinese backers of Manus, including HSG, ZhenFund, and Tencent, plan to buy the AI startup back from Meta at the $2B price Meta paid (The Information)
Techmeme
Tencent-backed Enflame receives approval for a Shanghai IPO and plans to raise ~$888M; Enflame is the last of China's four leading AI chipmakers to go to market (April Ma/Bloomberg)
Techmeme
Shifting to AI model customization is an architectural imperative
In the early days of large language models (LLMs), we grew accustomed to massive 10x jumps in reasoning and coding capability with every new model iteration. Today, those jumps have flattened into incremental gains. The exception is domain-specialized intelligence, where true step-function improvements are still the norm. When a model is fused with an organization’s…
Enabling a new model for healthcare with AI co-clinician
DeepMind Blog
Last cached leaderboard date: June 18, 2026. This model page is generated from the AskClash LLM Leaderboard cache and linked from the live leaderboard.