Skip to content
ModelCap

Head-to-head comparison

Claude Opus 5 vs Hy4 preview

Claude Opus 5 (Anthropic) and Hy4 preview (Tencent) compared on the ModelCap Index, API price, context window, provider availability, weight access and every public benchmark board they share. Figures are the same ones shown on the live rankings; nothing here is a hidden score.

Snapshot as of 3 September 2026

As of 3 September 2026, Claude Opus 5 holds the stronger ModelCap Index position (#3 vs #19); Hy4 preview is 10× cheaper per output token ($2.50/1M vs $25.00/1M); and Hy4 preview ships open weights.

Which should you choose?

Choose Claude Opus 5 if…

  • you want the stronger overall ModelCap Index position — #3 against #19 (83.6 vs 68.6 points).
  • you want provider choice — 5 listed API providers against 1.

Choose Hy4 preview if…

  • API cost matters — $2.50/1M output tokens against $25.00/1M, about 10× cheaper.
  • your workload is prompt-heavy — input tokens cost $0.834/1M against $5.00/1M.
  • you want to self-host: Hy4 preview ships open weights while Claude Opus 5 is api only.
  • you want the more recently listed model — Hy4 preview was listed 28 August 2026, Claude Opus 5 24 July 2026.

Claude Opus 5 vs Hy4 preview: specs, pricing and context

Specification comparison of Claude Opus 5 and Hy4 preview
FieldClaude Opus 5AnthropicHy4 previewTencent
ModelCap Index position#3#19
Index score83.668.6
EvidenceMeasuredEstimated
Input price / 1M tokens$5.00$0.834
Output price / 1M tokens$25.00$2.50
Context window1M tokens1M tokens
Max output tokens128K64K
API providers listed51
Weight accessAPI onlyOpen weights
Input modalitiesText, Image, FileText
First listed24 July 202628 August 2026
PublisherAnthropicTencent

Evidence: 6 public benchmark observations across 6 boards · placed against measured peers on publisher-reported benchmarks, discounted for self-report optimism; floored directly above its measured family predecessor. Prices are the lowest listed API offer per million tokens observed on the OpenRouter catalogue.

Benchmark scores: Claude Opus 5 vs Hy4 preview

Public benchmark boards where Claude Opus 5 or Hy4 preview has a published result
BoardClaude Opus 5Hy4 previewLeads
Arena codingArena (LMArena)15331526–1541HighOnly one result
LMArena AgentLMArena13.8%12.0%–15.6%HighOnly one result
ARC-AGI-2ARC Prize Foundation90.4%MaxOnly one result
ARC-AGI-3ARC Prize Foundation30.2%HighOnly one result
AA Intelligence IndexArtificial Analysis63.1intelligence-indexOnly one result
AA Terminal-Bench 2.1Artificial Analysis89.1%terminal-bench-2.1Only one result
AA Humanity's Last ExamArtificial Analysis54.9%humanitys-last-examOnly one result
Terminal-Bench 4.0Terminal-Bench (Laude Institute)51.8%48.4%–55.2%Claude Code · MaxOnly one result

Scores are the sources' own published figures for each model's best evaluated configuration; ModelCap never re-runs a benchmark.

Want a different pairing? Open the interactive comparison tool to swap either model for any current ranked language model.

Claude Opus 5 vs Hy4 preview: common questions

Is Claude Opus 5 better than Hy4 preview?

Claude Opus 5 ranks higher on the ModelCap Index as of 3 September 2026: #3 against #19. That is a capability ranking built from public benchmark evidence with published uncertainty; whether it is "better" for you also depends on price, context and where you can run it.

Is Claude Opus 5 cheaper than Hy4 preview?

Hy4 preview is cheaper on output tokens: $2.50/1M against $25.00/1M. Input tokens are $5.00/1M for Claude Opus 5 and $0.834/1M for Hy4 preview. Prices are the lowest listed API offer ModelCap observed, in USD per million tokens.

Which has the bigger context window, Claude Opus 5 or Hy4 preview?

Both publish a 1M-token context window.

Which is better for coding, Claude Opus 5 or Hy4 preview?

The two models do not share a coding benchmark board on ModelCap yet, so no head-to-head coding score is published; the ModelCap Index position is the closest overall signal.

Are Claude Opus 5 and Hy4 preview open-weight models?

Claude Opus 5: API only. Hy4 preview: Open weights. Open weights mean the checkpoint can be downloaded and self-hosted under its licence; API-only models are available solely through hosted endpoints.

Where can I run Claude Opus 5 and Hy4 preview?

ModelCap currently lists 5 API providers for Claude Opus 5 and 1 for Hy4 preview, from the OpenRouter catalogue snapshot the site serves; each model page lists the providers and their prices.

How current is this Claude Opus 5 vs Hy4 preview comparison?

Every figure comes from the sealed ModelCap dataset published 3 September 2026; the page re-renders within a minute of each data refresh, and the ModelCap Index positions are the same ones shown on the live rankings.

Explore further