Claude Opus 5.5 vs Hy4 preview: Specs & Benchmark Comparison

Claude Opus 5.5 is developed by Anthropic, while Hy4 preview comes from Tencent. Hy4 preview was released in August 2026, and Claude Opus 5.5 followed a month later in September 2026. Hy4 preview has a published size of about 770 billion parameters; Anthropic has not disclosed the parameter count of Claude Opus 5.5.

The two models share 9 published benchmarks. Claude Opus 5.5 leads on 9 of them. The widest gaps are on Program Bench, where Claude Opus 5.5 scores 91.2% against 17.5%; ArXivMath, where Claude Opus 5.5 scores 91.2% against 66.6%. Averaged across everything we track, Claude Opus 5.5 sits at 71.1% and Hy4 preview at 58.7%.

Claude Opus 5.5 is available through an API at $4 per million input tokens with a 1M-token context window. We do not track a hosted API for Hy4 preview, so pricing and context cannot be compared directly.

CharacteristicClaude Opus 5.5Hy4 preview
CompanyAnthropicTencent
Release DateSeptember 22, 2026August 28, 2026
Parameters—770B
MultimodalYesNo
Context (input)1.0M—
Context (output)128K—
Input Price / 1M$4.00—
Output Price / 1M$20.00—
Average Score71.1%58.7%
Benchmarks
Program Bench91.2%17.5%
ArXivMath91.2%66.6%
SWE-Bench Pro89.9%65.7%
Humanity's Last Exam (no tools, text-only)64.4%43.4%
BioMysteryBench89.3%71.3%
Humanity's Last Exam (with tools, text-only)67.7%55.4%
SWE-bench Multilingual93.9%82.9%
AutomationBench40.0%32.1%
OfficeQA Pro67.7%66.2%

Visual Benchmark Comparison

Claude Opus 5.5
Hy4 preview
Program Bench0.9 vs 0.2
0.9
0.2
ArXivMath0.9 vs 0.7
0.9
0.7
SWE-Bench Pro0.9 vs 0.7
0.9
0.7
Humanity's Last Exam (no tools, text-only)0.6 vs 0.4
0.6
0.4
BioMysteryBench0.9 vs 0.7
0.9
0.7
Humanity's Last Exam (with tools, text-only)0.7 vs 0.6
0.7
0.6
SWE-bench Multilingual0.9 vs 0.8
0.9
0.8
AutomationBench0.4 vs 0.3
0.4
0.3
OfficeQA Pro0.7 vs 0.7
0.7
0.7

Verdict

Claude Opus 5.5 leads in 1 out of 2 comparison categories.

Overall Performance

Both models show comparable average scores: Claude Opus 5.5 — 0.7, Hy4 preview — 0.6.

Recency

Claude Opus 5.5 is newer: released 9/22/2026 vs 8/28/2026.

More About These Models

Related Comparisons

Frequently Asked Questions

Which is better for coding — Claude Opus 5.5 or Hy4 preview?
Direct comparison on the SWE-Bench benchmark is not available. We recommend reviewing other metrics on the comparison page.
Which model is cheaper — Claude Opus 5.5 or Hy4 preview?
API pricing data is available on the individual model pages.
Which has a larger context window — Claude Opus 5.5 or Hy4 preview?
Context window data is available on the individual model pages.

The Claude Opus 5.5 and Hy4 preview comparison is updated for 2026. Data includes benchmark results, API pricing, context window size and other specifications. For more detailed information, visit the Claude Opus 5.5 or Hy4 preview page. See also the complete list of AI model comparisons.