Skip to main content

Model comparison

Claude Opus 4.5 vs Hy3 Preview

Data verified

Head-to-head evidence from 15 shared benchmark results across 5 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

64.22/100
No comparison
N/A
4 category wins0 category wins

Public leaderboard positions: Claude Opus 4.5 #34 (Supported); Hy3 Preview unranked (Not scored). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Claude Opus 4.5 and Hy3 Preview share 15 comparable benchmark results. 4 of 8 categories are comparable. 44 results are unique to Claude Opus 4.5; 7 to Hy3 Preview.

Updated July 23, 2026
Shared results
15
Claude Opus 4.5 only
44
Hy3 Preview only
7
Comparable categories
4 / 8

Treat this as a split decision. Claude Opus 4.5 makes more sense if knowledge is the priority or you would rather avoid the extra latency and token burn of a reasoning model; Hy3 Preview is the better fit if you want the cheaper token bill or you need the larger 256K context window.

Confidence note. This is a partial-evidence comparison with 15 shared benchmark results across 5 evidence categories; 4 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

Claude Opus 4.5 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 Opus 4.5 is also the more expensive model on tokens at $5.00 input / $25.00 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. Hy3 Preview is the reasoning model in the pair, while Claude Opus 4.5 is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use. Hy3 Preview gives you the larger context window at 256K, compared with 200K for Claude Opus 4.5.

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 Opus 4.5 and Hy3 Preview
CategoryClaude Opus 4.5ΔHy3 Preview
KnowledgeClaude Opus 4.558.1Margin 24.3Hy3 Preview33.8
CodingClaude Opus 4.571.7Margin 13.9Hy3 Preview57.8
AgenticClaude Opus 4.562.6Margin 8.2Hy3 Preview54.4
Inst. FollowingClaude Opus 4.569.5Margin 6.4Hy3 Preview63.1
ReasoningClaude Opus 4.564.4MarginNo overlapHy3 PreviewNot measured
MathClaude Opus 4.557.5MarginNo overlapHy3 PreviewNot measured
MultilingualClaude Opus 4.585.7MarginNo overlapHy3 PreviewNot measured
MultimodalClaude Opus 4.569.9MarginNo overlapHy3 PreviewNot measured

Decisive benchmark drivers

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

More
A · Claude Opus 4.5B · Hy3 Preview
  1. SWE-bench Verified

    Coding
    Source ↗
    A 80.9%B 74.4%
    Winner: Claude Opus 4.5Δ 6.5
    SWE-bench Verified: Claude Opus 4.5 scored 80.9%; Hy3 Preview scored 74.4%. Claude Opus 4.5 wins this benchmark.
  2. HLE

    Knowledge
    Source ↗
    A 30.8%B 25.5%
    Winner: Claude Opus 4.5Δ 5.3
    HLE: Claude Opus 4.5 scored 30.8%; Hy3 Preview scored 25.5%. Claude Opus 4.5 wins this benchmark.
  3. IFBench

    Inst. Following
    Source ↗
    A 58%B 63.1%
    Winner: Hy3 PreviewΔ 5.1
    IFBench: Claude Opus 4.5 scored 58%; Hy3 Preview scored 63.1%. Hy3 Preview wins this benchmark.
  4. Terminal-Bench 2.0

    Agentic
    Source ↗
    A 59.3%B 54.4%
    Winner: Claude Opus 4.5Δ 4.9
    Terminal-Bench 2.0: Claude Opus 4.5 scored 59.3%; Hy3 Preview scored 54.4%. Claude Opus 4.5 wins this benchmark.
  5. GPQA

    Knowledge
    Source ↗
    A 87%B 87.2%
    Winner: Hy3 PreviewΔ 0.2
    GPQA: Claude Opus 4.5 scored 87%; Hy3 Preview scored 87.2%. Hy3 Preview wins this benchmark.

Operational comparison

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

MetricClaude Opus 4.5Hy3 PreviewComparison
Input / output priceUSD per 1M tokensClaude Opus 4.5$5 input / $25 outputHy3 Preview$0 input / $0 outputHy3 Preview has the lower combined listed price.
Generation speedtokens per secondClaude Opus 4.546 tok/sHy3 PreviewNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenClaude Opus 4.51.01 sHy3 PreviewNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensClaude Opus 4.5200KHy3 Preview256KHy3 Preview lists the larger context window.

Benchmark Deep Dive

AgenticClaude Opus 4.5 wins
BenchmarkClaude Opus 4.5Hy3 PreviewResult
Terminal-Bench 2.0Source 59.3%54.4%Claude Opus 4.5 leads
OSWorld-VerifiedSource 66.3%Not comparable
OSWorldSource 66.3%Not comparable
Claw-EvalSource 59.6%Not comparable
QwenClawBenchSource 52.3%Not comparable
τ³-bench resultsSource 70.2%Not comparable
VITA-BenchSource 23.3%Not comparable
DeepPlanningSource 26.4%Not comparable
ToolathlonSource 43.5%Not comparable
MCP AtlasSource 42.3%Not comparable
MCP-TasksSource 71.8%Not comparable
WideResearchSource 76.4%Not comparable
CyberGymSource 50.6%Not comparable
τ²-bench resultsSource 86.3%Not comparable
Gert LabsSource 64.23%36.91%Claude Opus 4.5 leads
JobBenchSource 32.3%Not comparable
AA Agentic IndexSource 30.7%Not comparable
GDPval-AASource 35.7%Not comparable
GDPval-AASource 1214Not comparable
CodingClaude Opus 4.5 wins
BenchmarkClaude Opus 4.5Hy3 PreviewResult
SWE-bench VerifiedSource 80.9%74.4%Claude Opus 4.5 leads
LiveCodeBench v6Source 84.8%Not comparable
SWE-bench ProSource 57.1%Not comparable
SWE MultilingualSource 77.5%Not comparable
NL2RepoSource 43.2%Not comparable
AA-SciCodeSource 47.0%47.6%Hy3 Preview leads
Terminal-Bench 2.0Source 54.4%Not comparable
SciCodeSource 41.2%Not comparable
AA Coding IndexSource 58.8%Not comparable
Reasoning
BenchmarkClaude Opus 4.5Hy3 PreviewResult
LongBench v2Source 64.4%Not comparable
AI-NeedleSource 74%Not comparable
AA-LCRSource 65.3%66.7%Hy3 Preview leads
CritPtSource 0.3%4.9%Hy3 Preview leads
KnowledgeClaude Opus 4.5 wins
BenchmarkClaude Opus 4.5Hy3 PreviewResult
GPQASource 87%87.2%Hy3 Preview leads
SuperGPQASource 70.6%Not comparable
MMLU-ProSource 89.5%Not comparable
MMLU-ReduxSource 96.6%Not comparable
C-EvalSource 92.2%Not comparable
HLESource 30.8%25.5%Claude Opus 4.5 leads
Artificial Analysis Intelligence IndexSource 34.7%41.2%Hy3 Preview leads
AA-GPQA DiamondSource 81.0%89.7%Hy3 Preview leads
AA-HLESource 12.9%31.6%Hy3 Preview leads
AA-Omniscience IndexSource -3.9%-18.5%Claude Opus 4.5 leads
AA-Omniscience AccuracySource 40.7%31.5%Claude Opus 4.5 leads
AA-Omniscience Hallucination RateSource 75.4%73.0%Hy3 Preview leads
AA MMLU-ProSource 88.9%Not comparable
GPQA-DSource 87.2%Not comparable
Math
BenchmarkClaude Opus 4.5Hy3 PreviewResult
AIME26Source 95.1%Not comparable
HMMT Feb 2025Source 92.9%Not comparable
HMMT Nov 2025Source 93.3%Not comparable
HMMT Feb 2026Source 85.3%Not comparable
MMAnswerBenchSource 84.0%Not comparable
FrontierMath v2 (Tiers 1-3)Source 20.690%Not comparable
FrontierMath v2 (Tier 4)Source 4.167%Not comparable
Multilingual
BenchmarkClaude Opus 4.5Hy3 PreviewResult
MMLU-ProXSource 85.7%Not comparable
NOVA-63Source 56.7%Not comparable
Multimodal
BenchmarkClaude Opus 4.5Hy3 PreviewResult
MMMU-ProSource 70.6%Not comparable
MathVisionSource 74.3%Not comparable
CharXivSource 68.5%Not comparable
VideoMMMUSource 84.4%Not comparable
ScreenSpot ProSource 45.7%Not comparable
V*Source 67.0%Not comparable
AA-MMMU-ProSource 71.2%Not comparable
Design Arena WebsiteSource 1277Not comparable
Inst. FollowingClaude Opus 4.5 wins
BenchmarkClaude Opus 4.5Hy3 PreviewResult
IFEvalSource 90.9%Not comparable
IFBenchSource 58%63.1%Hy3 Preview leads
AA-IFBenchSource 43.0%Not comparable
Frequently Asked Questions (5)

Which is better, Claude Opus 4.5 or Hy3 Preview?

Claude Opus 4.5 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 Opus 4.5 or Hy3 Preview?

Claude Opus 4.5 has the edge for knowledge tasks in this comparison, averaging 58.1 versus 33.8. Inside this category, AA-HLE is the benchmark that creates the most daylight between them.

Which is better for coding, Claude Opus 4.5 or Hy3 Preview?

Claude Opus 4.5 has the edge for coding in this comparison, averaging 71.7 versus 57.8. Inside this category, SWE-bench Verified is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Claude Opus 4.5 or Hy3 Preview?

Claude Opus 4.5 has the edge for agentic tasks in this comparison, averaging 62.6 versus 54.4. Inside this category, Gert Labs is the benchmark that creates the most daylight between them.

Which is better for instruction following, Claude Opus 4.5 or Hy3 Preview?

Claude Opus 4.5 has the edge for instruction following in this comparison, averaging 69.5 versus 63.1. Inside this category, IFBench 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.