Skip to main content

Claude Sonnet 4.6 vs Hy3

SpecClaude Sonnet 4.6Hy3
Respan Index37.2 (#74)39.5 (#71)
Blended price per 1M$6$0.23
Context window1M256K
Input / output per 1M$3 / $15$0.13 / $0.528
Max output128K-
Inputtext, visiontext
Released2026-02-172026-07-06

Respan Index by category

Each category is scored 0 to 100, and how far ahead the winner is. Leads under a point are close to even.

CategoryClaude Sonnet 4.6Hy3
Coding14.9 Claude Sonnet 4.616.4 Hy3
Agents50.8 Claude Sonnet 4.651.1 Hy3
Reasoning36.4 Claude Sonnet 4.643.4 Hy3
Knowledge & language35.7 Claude Sonnet 4.637.5* Hy3
Human preference54.3 Claude Sonnet 4.653.7 Hy3

* Estimated: no published scores in that category. How the Respan Index works

Benchmarks both report

They split the 6 benchmarks both report evenly. Higher is better. Each score links to where it was published.

BenchmarkClaude Sonnet 4.6Hy3
LMArena WebDev (LMArena)15221506
LMArena Elo14721454
GPQA Diamond89.9%90.4%
Humanity's Last Exam (no tools)33.2%37%
MCP Atlas61.3%79.1%
SWE-bench Verified79.6%78%

FAQ

Is Claude Sonnet 4.6 better than Hy3?

Hy3 scores 39.5 on the Respan Index (#71), ahead of Claude Sonnet 4.6 at 37.2 (#74). They split the 6 benchmarks both report evenly.

Which is cheaper, Claude Sonnet 4.6 or Hy3?

Claude Sonnet 4.6 lists at $3 input and $15 output per 1M tokens; Hy3 at $0.13 and $0.528. Hy3 is 26x cheaper per token at list price.

Which has the larger context window?

Claude Sonnet 4.6 accepts 1M tokens and Hy3 256K tokens.

Compare other models

vs

Built for AI agents.
Break less.
Ship more.