Hy3 vs Claude Sonnet 5

The Apache Agent vs The Proprietary Coder

July 7, 2026 · 10 min read

TL;DR: Claude Sonnet 5 leads every shared benchmark — SWE-bench Pro (+5.3), Terminal-Bench 2.1 (+8.7), HLE w/tools (+4.2). But Hy3 fights to a near-tie on BrowseComp (84.2 vs 84.7), dominates MCP Atlas (79.1% — #3 overall), DeepSearchQA (91.0%), and costs 12.5× less ($0.80 vs $10/1M output). Sonnet 5 is the better coder. Hy3 is the better open-weight agent — at 1/12th the price.
295B
Hy3 Total Params
Sonnet 5 (undisclosed)
Apache 2.0
Hy3 License
Proprietary
Sonnet 5 License
$0.80
Hy3 Output /1M tok
$10.00
Sonnet 5 Output (intro)

Two Very Different Philosophies

Tencent Hy3 (July 6, 2026) is an open-weight 295B MoE under Apache 2.0 — 21B active parameters, 192 experts, $0.20/$0.80 per 1M tokens. Built in under 90 days and hardened through 50+ internal Tencent products, it prioritizes reliability: hallucination rates dropped 57%, commonsense errors halved, and tool calls work consistently across scaffolds.

Claude Sonnet 5 (June 30, 2026) is Anthropic's proprietary Sonnet-tier flagship — "the most agentic Sonnet yet." It uses adaptive thinking, has a 1M context window (4× Hy3's 256K), and launched at $2/$10 per 1M tokens (through Aug 31), then $3/$15. Anthropic doesn't disclose parameter counts. It's available on Anthropic API, Bedrock, and Vertex AI.

"Sonnet 5's selling point isn't price. It's the out-of-the-box agentic polish — planning and self-checking that open-weight models still struggle with." — Binary Verse AI

Coding: Sonnet 5 Leads Decisively

BenchmarkHy3Sonnet 5ΔWinner
SWE-bench Verified78.085.2+7.2Sonnet
SWE-bench Multilingual75.878.3+2.5Sonnet
SWE-bench Pro ★57.963.2+5.3Sonnet
Terminal-Bench 2.171.780.4+8.7Sonnet
FrontierCode v138.8Sonnet*
Coding benchmarks chart

The SWE-bench Verified gap (+7.2) and Terminal-Bench lead (+8.7) are the most telling for developers. Sonnet 5 is meaningfully better at real GitHub issue resolution and CLI operations. But note: Sonnet 5's 63.2% Pro costs $10/1M. Hy3's 57.9% costs $0.80/1M. That's 91.7% of the Pro capability at 8% of the price.

Agents & Search: Near-Ties Where It Matters

BenchmarkHy3Sonnet 5ΔWinner
BrowseComp ★84.284.7+0.5~Tie
MCP Atlas (Public)79.1Hy3*
DeepSearchQA91.0Hy3*
OSWorld-Verified81.2Sonnet*

* Not published by the other vendor

Agent benchmarks chart

Hy3's MCP Atlas score of 79.1% — #3 overall, #1 open-weight — is a genuinely impressive result. The BrowseComp near-tie (84.2 vs 84.7) is the most actionable signal: on Anthropic's own agentic search benchmark, a $0.80/1M open-weight model is 0.5 points behind a $10/1M proprietary model.

Reasoning & STEM

BenchmarkHy3Sonnet 5ΔWinner
GPQA Diamond90.491.1+0.7~Tie
HLE (with tools)53.257.4+4.2Sonnet
HLE (no tools)37.043.2+6.2Sonnet
USAMO 202672.0Hy3*
Radar chart

The Economics: 12.5× Price Gap

MetricHy3Sonnet 5 (intro)Sonnet 5 (std)
Input /1M tok$0.20$2.00$3.00
Output /1M tok$0.80$10.00$15.00
Output Multiplier12.5×18.75×
Context256K1M1M
LicenseApache 2.0ProprietaryProprietary
Cost chart

For 100M output tokens/month: Hy3 costs $80. Sonnet 5 costs $1,000 (intro) or $1,500 (standard). And there's the tokenizer caveat: Sonnet 5's updated tokenizer produces 1.0-1.35× more tokens for the same input, meaning your effective cost per character increases after the introductory period ends.

Value scatter

The Self-Hosting Factor

Claude Sonnet 5 cannot be self-hosted. Hy3, under Apache 2.0, can run on your own hardware — 295B total / 21B active fits a 2× DGX Spark configuration. For regulated industries, this alone may be the deciding factor.

10-Point Verdict

🔧 Repository-Scale Coding
Sonnet 5 (+5.3 Pro, +7.2 Verified)
🖥️ CLI / Terminal Tasks
Sonnet 5 (+8.7 TB 2.1)
🔗 Tool Orchestration (MCP)
Hy3 (79.1% — #3 overall)
🔍 Web Search & Browsing
~Tie (BrowseComp 84.2 vs 84.7)
🧠 Reasoning & STEM
Sonnet 5 (+0.7 GPQA, +4.2 HLE)
💰 Cost Efficiency
Hy3 (12.5-18.75× cheaper)
📏 Context Window
Sonnet 5 (1M vs 256K)
🛡️ Production Reliability
Hy3 (57% less hallucination)
🏠 Self-Hosting
Hy3 (Apache 2.0, 2× DGX Spark)
🏢 Enterprise Readiness
Sonnet 5 (Bedrock, Vertex, SLA)

Which One?

Choose Sonnet 5 if:

  • Coding is paramount. +5.3 Pro, +7.2 Verified, +8.7 TB 2.1 are decisive.
  • You need 1M context. For long-horizon coding sessions across many files.
  • You want managed infra. Bedrock, Vertex, Anthropic API — zero DevOps.
  • You're in the Anthropic ecosystem. Claude Code, prompt caching, computer use.

Choose Hy3 if:

  • Cost matters at scale. 12.5× cheaper at intro, 18.75× after August.
  • You need to self-host. Apache 2.0, fits consumer hardware.
  • You're building agents. MCP Atlas 79.1%, BrowseComp near-tie, DeepSearchQA 91.0%.
  • You want predictable token economics. No tokenizer surprises, no pricing cliffs.

The Bottom Line

Claude Sonnet 5 is the better coder. Hy3 is the better value agent. At 12.5× the price, Sonnet 5 delivers +5.3 Pro points — a premium justified for code-heavy workloads. But for agent workloads, the BrowseComp near-tie suggests the open-weight vs proprietary gap has nearly closed. Pick your weapon.

Test Both on Real Code

20+ LLMs on CodingFleet. Run Hy3 and Sonnet 5 side-by-side.

🚀 Try on CodingFleet →

Sources: Tencent · Anthropic · System Card · Vellum · Emergent.sh. Vendor-reported scores unless noted.