Compare/Trinity-Large-Thinking vs Tencent Hy3 Preview

AI tool comparison

Trinity-Large-Thinking vs Tencent Hy3 Preview

Which one should you ship with? Here is the side-by-side panel verdict, pricing read, reviewer split, and community vote comparison.

T

Open Source Models

Trinity-Large-Thinking

399B open MoE reasoning model that's 96% cheaper than Claude Opus

Ship

75%

Panel ship

Community

Free

Entry

Trinity-Large-Thinking is a 399-billion-parameter open mixture-of-experts (MoE) reasoning model from Arcee AI, released under Apache 2.0. It's designed specifically for long-horizon multi-turn tool use and autonomous agentic tasks — thinking before responding with an explicit reasoning chain. The model ranked #2 on PinchBench (behind only Claude Opus 4.6) while costing $0.90/M output tokens via the Arcee API — roughly 96% cheaper than Opus. The full weights are freely downloadable from Hugging Face, making it one of the most capable openly-downloadable models available anywhere. Architecturally it draws on MoE efficiency to activate only a fraction of parameters per forward pass, enabling the massive 399B count without proportional compute cost. For teams building production agents that need serious reasoning but can't afford closed-model pricing at scale, Trinity-Large-Thinking is the most compelling open alternative that's appeared in a long time.

T

AI Models

Tencent Hy3 Preview

295B MoE open weights — China's most efficient frontier model yet

Ship

75%

Panel ship

Community

Paid

Entry

Tencent open-sourced Hy3 Preview on April 23, 2026 — the first model to emerge from the company's rebuilt AI infrastructure, and its most credible challenge to frontier closed models to date. With 295 billion total parameters but only 21 billion active at inference time (plus 3.8B MTP layer parameters), it's a Mixture-of-Experts architecture that punches far above its compute weight. The model supports up to 256K context and is available via Hugging Face, ModelScope, and GitCode under the Tencent Hy Community License. On coding benchmarks, Hy3 scores 74.4% on SWE-bench Verified, 54.4% on Terminal-Bench 2.0, and 67.1% on BrowseComp — placing it firmly in the same tier as top models from Anthropic and OpenAI. Tencent claims a 40% efficiency improvement over its predecessor Hunyuan models, and pricing through Tencent Cloud TokenHub is aggressive: RMB 1.2 per million input tokens. A free two-week window at launch via OpenRouter made it widely accessible immediately. The model was led by a team that includes former OpenAI researchers and has already been deployed across Tencent's core products — WeChat, Yuanbao, and QQ. That production integration is a meaningful signal: this isn't a benchmark vanity release. For developers who need a powerful, cost-efficient reasoning and agentic model with actual open weights, Hy3 Preview is one of the most interesting drops of April 2026.

Decision
Trinity-Large-Thinking
Tencent Hy3 Preview
Panel verdict
Ship · 3 ship / 1 skip
Ship · 3 ship / 1 skip
Community
No community votes yet
No community votes yet
Pricing
$0.90/M output tokens (Arcee API) / Free weights (Apache 2.0)
Open Weights (Tencent Hy Community License); API from RMB 1.2/M tokens
Best for
399B open MoE reasoning model that's 96% cheaper than Claude Opus
295B MoE open weights — China's most efficient frontier model yet
Category
Open Source Models
AI Models

Reviewer scorecard

Builder
80/100 · ship

Near-Opus-level reasoning at $0.90/M tokens is the pricing inflection I've been waiting for. Apache 2.0 weights mean I can self-host for compliance-sensitive use cases. Already benchmarking it as a drop-in for my agent evaluation pipeline.

80/100 · ship

21B active params with 295B total — this is genuinely practical to deploy on reasonable hardware while matching models 10x the inference cost. The 256K context and strong SWE-bench score make it a legitimate option for agentic coding pipelines. I'd use this today.

Skeptic
45/100 · skip

Preview weights and PinchBench rankings tell part of the story — real-world agentic performance on messy production tasks is another matter. Arcee AI isn't Anthropic or Google; sustaining a 399B model with quality ongoing RLHF is expensive and the preview label is a yellow flag.

45/100 · skip

The Tencent Hy Community License is not Apache 2.0 or MIT — read it carefully before using this in production. There are usage restrictions that could bite commercial deployments. Also, benchmark scores look great, but independent evals of Chinese labs' models have historically diverged from self-reported numbers.

Futurist
80/100 · ship

A US-built, Apache-licensed frontier reasoning model competitive with closed offerings fundamentally changes the open-source AI landscape. The talent and capital required to do this was thought to only exist at the biggest labs. Arcee just proved otherwise.

80/100 · ship

The MoE efficiency race is the actual story here — we're getting frontier-class capability at a fraction of the activation cost. Hy3 is proof that the compute-vs-capability Pareto frontier keeps moving. Open weights with real deployment signals (WeChat at scale) is a combination that matters.

Creator
80/100 · ship

The thinking chain output is remarkably coherent for creative briefs and long-form narrative planning. At this price point I can run draft-then-refine pipelines at scale without budget anxiety. A genuine Ship for creative workflows.

80/100 · ship

Strong visual coding capabilities and multimodal understanding make this genuinely useful for design-to-code workflows. The health image analysis and product comparison use cases already deployed in Yuanbao show real-world creative utility beyond pure benchmark games.

Weekly AI Tool Verdicts

Get the next comparison in your inbox

New AI tools ship daily. We compare them before you waste an afternoon.

Bookmarks

Loading bookmarks...

No bookmarks yet

Bookmark tools to save them for later