Skip to main content

Model comparison

Claude Sonnet 5 vs Hy3 Preview

Data verified

Head-to-head evidence from 17 shared benchmark results across 4 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

65.32/100
No comparison
N/A
3 category wins0 category wins

Public leaderboard positions: Claude Sonnet 5 #29 (Estimated); Hy3 Preview unranked (Not scored). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Claude Sonnet 5 and Hy3 Preview share 17 comparable benchmark results. 3 of 8 categories are comparable. 19 results are unique to Claude Sonnet 5; 5 to Hy3 Preview.

Updated July 23, 2026
Shared results
17
Claude Sonnet 5 only
19
Hy3 Preview only
5
Comparable categories
3 / 8

Treat this as a split decision. Claude Sonnet 5 makes more sense if agentic is the priority or you need the larger 1M context window; Hy3 Preview is the better fit if you want the cheaper token bill.

Confidence note. This is a partial-evidence comparison with 17 shared benchmark results across 4 evidence categories; 3 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

Claude Sonnet 5 and Hy3 Preview finish on the same BenchAlign overall score, so this is less about a single winner and more about where the edge shows up. The BenchAlign headline says tie; the benchmark table is where the real choice happens.

Claude Sonnet 5 is also the more expensive model on tokens at $2.00 input / $10.00 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for Hy3 Preview. That is roughly Infinityx on output cost alone. Claude Sonnet 5 gives you the larger context window at 1M, compared with 256K for Hy3 Preview.

Category breakdown

Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.

Category scores and score margins for Claude Sonnet 5 and Hy3 Preview
CategoryClaude Sonnet 5ΔHy3 Preview
AgenticClaude Sonnet 581.9Margin 27.5Hy3 Preview54.4
KnowledgeClaude Sonnet 557.4Margin 23.6Hy3 Preview33.8
CodingClaude Sonnet 576.7Margin 18.9Hy3 Preview57.8
MultimodalClaude Sonnet 588.3MarginNo overlapHy3 PreviewNot measured
Inst. FollowingClaude Sonnet 5Not measuredMarginNo overlapHy3 Preview63.1

Decisive benchmark drivers

The largest measured benchmark gaps in this matchup, with exact reported values.

More
A · Claude Sonnet 5B · Hy3 Preview
  1. HLE

    Knowledge
    Source ↗
    A 57.4%B 25.5%
    Winner: Claude Sonnet 5Δ 31.9
    HLE: Claude Sonnet 5 scored 57.4%; Hy3 Preview scored 25.5%. Claude Sonnet 5 wins this benchmark.
  2. Terminal-Bench 2.0

    Agentic
    Source ↗
    A 80.4%B 54.4%
    Winner: Claude Sonnet 5Δ 26
    Terminal-Bench 2.0: Claude Sonnet 5 scored 80.4%; Hy3 Preview scored 54.4%. Claude Sonnet 5 wins this benchmark.
  3. SWE-bench Verified

    Coding
    Source ↗
    A 85.2%B 74.4%
    Winner: Claude Sonnet 5Δ 10.8
    SWE-bench Verified: Claude Sonnet 5 scored 85.2%; Hy3 Preview scored 74.4%. Claude Sonnet 5 wins this benchmark.

Operational comparison

Runtime and commercial metrics are compared only when both models have a complete sourced value.

MetricClaude Sonnet 5Hy3 PreviewComparison
Input / output priceUSD per 1M tokensClaude Sonnet 5$2 input / $10 outputHy3 Preview$0 input / $0 outputHy3 Preview has the lower combined listed price.
Generation speedtokens per secondClaude Sonnet 5Not availableHy3 PreviewNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenClaude Sonnet 5Not availableHy3 PreviewNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensClaude Sonnet 51MHy3 Preview256KClaude Sonnet 5 lists the larger context window.

Benchmark Deep Dive

AgenticClaude Sonnet 5 wins
BenchmarkClaude Sonnet 5Hy3 PreviewResult
Terminal-Bench 2.0Source 80.4%54.4%Claude Sonnet 5 leads
BrowseCompSource 84.7%Not comparable
HLE w/ toolsSource 57.4%Not comparable
OSWorld-VerifiedSource 81.2%Not comparable
GDPval-AASource 16071214Claude Sonnet 5 leads
AA Agentic IndexSource 46.7%30.7%Claude Sonnet 5 leads
GDPval-AASource 55.4%35.7%Claude Sonnet 5 leads
AA BriefcaseSource 1388Not comparable
AA AutomationBenchSource 39.2%Not comparable
AA EnterpriseOps-GymSource 44.7%Not comparable
AA Harvey LABSource 90.1%Not comparable
AA Tau3 BankingSource 28.2%Not comparable
aaTerminalBench21Source 80.5%Not comparable
Gert LabsSource 36.91%Not comparable
CodingClaude Sonnet 5 wins
BenchmarkClaude Sonnet 5Hy3 PreviewResult
SWE-bench VerifiedSource 85.2%74.4%Claude Sonnet 5 leads
SWE-bench ProSource 63.2%Not comparable
SWE MultilingualSource 78.3%Not comparable
SWE MultimodalSource 28.1%Not comparable
Terminal-Bench 2.0Source 80.4%54.4%Claude Sonnet 5 leads
FrontierCode 1.1 MainSource 42.7%Not comparable
cursorBench32Source 61.5%Not comparable
AA Coding IndexSource 71.5%58.8%Claude Sonnet 5 leads
AA-SciCodeSource 53.6%47.6%Claude Sonnet 5 leads
SciCodeSource 41.2%Not comparable
Reasoning
BenchmarkClaude Sonnet 5Hy3 PreviewResult
AA-LCRSource 70.7%66.7%Claude Sonnet 5 leads
CritPtSource 16.9%4.9%Claude Sonnet 5 leads
KnowledgeClaude Sonnet 5 wins
BenchmarkClaude Sonnet 5Hy3 PreviewResult
HLESource 57.4%25.5%Claude Sonnet 5 leads
HLE w/o toolsSource 43.2%Not comparable
Artificial Analysis Intelligence IndexSource 53.4%41.2%Claude Sonnet 5 leads
AA-GPQA DiamondSource 91.1%89.7%Claude Sonnet 5 leads
AA-HLESource 39.6%31.6%Claude Sonnet 5 leads
AA-Omniscience IndexSource 15.3%-18.5%Claude Sonnet 5 leads
AA-Omniscience AccuracySource 38.3%31.5%Claude Sonnet 5 leads
AA-Omniscience Hallucination RateSource 37.3%73.0%Claude Sonnet 5 leads
GPQASource 87.2%Not comparable
GPQA-DSource 87.2%Not comparable
Multimodal
BenchmarkClaude Sonnet 5Hy3 PreviewResult
CharXivSource 88.3%Not comparable
CharXiv w/o toolsSource 77%Not comparable
AA-MMMU-ProSource 77.3%Not comparable
Design Arena WebsiteSource 1314Not comparable
Inst. Following
BenchmarkClaude Sonnet 5Hy3 PreviewResult
IFBenchSource 63.1%Not comparable
Frequently Asked Questions (4)

Which is better, Claude Sonnet 5 or Hy3 Preview?

Claude Sonnet 5 and Hy3 Preview are tied on the BenchAlign overall score, so the right pick depends on which category matters most for your use case.

Which is better for knowledge tasks, Claude Sonnet 5 or Hy3 Preview?

Claude Sonnet 5 has the edge for knowledge tasks in this comparison, averaging 57.4 versus 33.8. Inside this category, AA-Omniscience Hallucination Rate is the benchmark that creates the most daylight between them.

Which is better for coding, Claude Sonnet 5 or Hy3 Preview?

Claude Sonnet 5 has the edge for coding in this comparison, averaging 76.7 versus 57.8. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Claude Sonnet 5 or Hy3 Preview?

Claude Sonnet 5 has the edge for agentic tasks in this comparison, averaging 81.9 versus 54.4. Inside this category, GDPval-AA is the benchmark that creates the most daylight between them.

Related Comparisons

Last updated: July 23, 2026

Choose a model with this week’s evidence

Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.

One email each week. Unsubscribe anytime.