Tencent

Hy3 Preview

A sparse reasoning, coding, and tool-use model.

open-weightsreasoningcodingagents

Model record

Hy3 Preview model overview

Hy3 Preview is a open weights model from Tencent. It was released on May 31, 2026. Its strongest case is 256k context, while buyers should account for weight license unavailable.

Hy3 Preview benchmark snapshot

EvaluationReported scoreWhat it probes
MMLU-ProNot reportedBroad knowledge and multi-step reasoning
GPQA DiamondNot reportedGraduate-level science reasoning
SWE-bench VerifiedNot reportedVerified real-repository issue resolution
LiveCodeBenchNot reportedContamination-aware competitive programming
SWE-Bench ProNot reportedLonger, harder professional software tasks
Artificial Analysis Intelligence IndexNot reportedComposite third-party capability index; version matters

Scores are percentages reported by model creators or benchmark maintainers under varying settings. A blank is preferable to an inferred result. See our methodology.

Hy3 Preview strengths

  • 256K context
  • Downloadable weights
  • Fast and slow reasoning

Hy3 Preview limitations

  • Weight license unavailable
  • Combined weights and API access do not fit the access field
Editorial take: Benchmark rank should narrow a shortlist, not close a purchase. Run a private evaluation with representative prompts, failure cases, latency targets, and total token costs.

Source record

Specifications and scores are linked to the best source located during review. Provider-reported results are not presented as third-party lab reproductions.

Source limitation: Official model card: https://huggingface.co/tencent/Hy3-preview

Read Tencent Hy3 Preview announcement