Agentic
Directional only- Claude Opus 5
- 77.4
- Supported · #2/151
- Hy3 Preview
- 49.9
- Estimated · #66/151
- Basis
- BenchAlign lane · 19 vs 2 public rows
- Reading
- Directional only
Claude Opus 5 vs Hy3 Preview
Updated September 4, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
Decision reading
Claude Opus 5 has the higher public score, 80.66 versus 57.08, and the 90% score intervals do not overlap.
1 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
Share or export
Which one for your work
Recommendations appear only when a shared evidence basis or an explicit operating constraint supports the call. Secondary and unsupported use cases stay disclosed below the initial list.
Long documents
Prompts that approach the documented context limit
Claude Opus 5
Claude Opus 5 has the larger documented context window.
Confidence: documented
Show secondary and unsupported calls
Coding work
Code generation, repair, and software-engineering tasks
Not enough matched evidence
Hy3 Preview is scored on Estimated evidence for coding, so the reading is directional rather than like-for-like.
Confidence: limited
Agentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
Hy3 Preview is scored on Estimated evidence for agentic, so the reading is directional rather than like-for-like.
Confidence: limited
Chat turn cost
1K fresh input + 500 output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-rates
Cache-heavy agent loop cost
200K cached + 20K fresh input + 10K output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-rates
Repository review cost
50K fresh input + 3K output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-rates
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
72 Claude Opus 5 only
1 Shared
5 Hy3 Preview only
- Shared results
- 1
- Claude Opus 5 only
- 72
- Hy3 Preview only
- 5
- Like-for-like categories
- 0 / 8
3 categories rest on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.
Category results, on a stated basis
Each row shows the public-lane category score for both models: the BenchAlign lane for agentic, coding, and knowledge, and the weighted public rows elsewhere, with the same rank each model page reports. A row is like-for-like only when both scores rest on Supported evidence or the same weighted set. Directional and not-comparable rows remain visible, but they never receive a winner.
Coding
Directional only- Claude Opus 5
- 75.6
- Supported · #3/183
- Hy3 Preview
- 45.9
- Estimated · #103/183
- Basis
- BenchAlign lane · 16 vs 2 public rows
- Reading
- Directional only
Knowledge
Directional only- Claude Opus 5
- 82.1
- Supported · #3/181
- Hy3 Preview
- 50.6
- Estimated · #86/181
- Basis
- BenchAlign lane · 19 vs 2 public rows
- Reading
- Directional only
Reasoning
Not comparable- Claude Opus 5
- 75.6
- #13/22
- Hy3 Preview
- Not ranked
- Basis
- Provisional lane · 2 vs 0 weighted rows
- Reading
- Not comparable
Math
Not comparable- Claude Opus 5
- Not ranked
- Hy3 Preview
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Multilingual
Not comparable- Claude Opus 5
- Not ranked
- Hy3 Preview
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Multimodal
Not comparable- Claude Opus 5
- 88.7
- #2/48
- Hy3 Preview
- Not ranked
- Basis
- Provisional lane · 1 vs 0 weighted rows
- Reading
- Not comparable
Instruction following
Not comparable- Claude Opus 5
- Not ranked
- Hy3 Preview
- 54.8
- #74/120
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
| Category | Claude Opus 5 | Hy3 Preview | Basis | Reading |
|---|---|---|---|---|
| Agentic | 77.4Supported · #2/151 | 49.9Estimated · #66/151 | Directional onlyBenchAlign lane · 19 vs 2 public rows | Directional only |
| Coding | 75.6Supported · #3/183 | 45.9Estimated · #103/183 | Directional onlyBenchAlign lane · 16 vs 2 public rows | Directional only |
| Knowledge | 82.1Supported · #3/181 | 50.6Estimated · #86/181 | Directional onlyBenchAlign lane · 19 vs 2 public rows | Directional only |
| Reasoning | 75.6#13/22 | Not ranked | Not comparableProvisional lane · 2 vs 0 weighted rows | Not comparable |
| Math | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Multimodal | 88.7#2/48 | Not ranked | Not comparableProvisional lane · 1 vs 0 weighted rows | Not comparable |
| Instruction following | Not ranked | 54.8#74/120 | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
Ranks count the models scored in each category’s lane, so the agentic, coding, and knowledge denominators (BenchAlign) differ from the provisional-lane categories. Unranked scores sit on the lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.
Shape of the matched evidence
Only shared public evidence is shown. Sparse evidence stays a ruled list rather than being closed into a radar shape.
Too few matched category axes support a radar. The ruled list below shows only shared benchmark results; positions use each benchmark’s normalized display scale when available.
SWE-bench Verified
Coding
What each workload costs
Three fixed token mixes turn per-token rates into comparable decisions. Each scenario states context fit and whether cached input had to fall back to the published list-input rate.
Chat turn
1K fresh input + 500 output tokens
- Claude Opus 5
- $0.0175
- Fits in one request
- Hy3 Preview
- Self-hosted; infrastructure cost varies
- Fits in one request
Hy3 Preview has no comparable published API token rate.
Repository review
50K fresh input + 3K output tokens
- Claude Opus 5
- $0.325
- Fits in one request
- Hy3 Preview
- Self-hosted; infrastructure cost varies
- Fits in one request
Hy3 Preview has no comparable published API token rate.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- Claude Opus 5
- $0.45
- Fits in one request
- Hy3 Preview
- Self-hosted; infrastructure cost varies
- Fits in one request
- Cached-input rate unavailable
Hy3 Preview has no comparable published API token rate.
Specification differences
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
SpecificationClaude Opus 5Hy3 Preview
Context window
Maximum documented context; output-token limits may be lower.
Claude Opus 5
Hy3 Preview
256K
API model ID
Claude Opus 5
claude-opus-5
Anthropic model overviewHy3 Preview
Not sourced
Cached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Claude Opus 5
$0.5 per 1M cached input tokens
Claude API pricingHy3 Preview
No comparable hosted API rate
Documented inputs
Claude Opus 5
text, image
Anthropic model overviewHy3 Preview
Not sourced
Documented outputs
Claude Opus 5
Hy3 Preview
Not sourced
Provider availability
Claude Opus 5
Generally Available · Claude API
Anthropic model overviewHy3 Preview
Not sourced
Reasoning profile
Claude Opus 5
Reasoning
Hy3 Preview
Reasoning
Weight access
Claude Opus 5
Proprietary
Hy3 Preview
Open Weight
License
Claude Opus 5
Proprietary
Hy3 Preview
Open Weight
Release date
Claude Opus 5
2026-07-24
Hy3 Preview
2026-04-23
If you already use one of these models
- Deployment change
- The models list different providers, so authentication, endpoint behavior, limits, and feature support may change.
- Quality signal
- Claude Opus 5 has the higher public score, 80.66 versus 57.08, and the 90% score intervals do not overlap.
- Workload cost
- A complete comparable API-rate estimate is not available for both models.
- Context tradeoff
- Claude Opus 5 has the larger documented window (1M).
Run the same representative tasks against both endpoints before changing production traffic.
Benchmark evidence
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Browse raw public benchmark evidence78 rows
Agentic
Terminal-Bench 3.0
Claude Opus 542.7%SourceHy3 Preview—Not directly comparable
BrowseComp
Claude Opus 590.8%SourceHy3 Preview—Not directly comparable
HLE w/ tools
Claude Opus 564.7%SourceHy3 Preview—Not directly comparable
DeepSearchQA
Claude Opus 595.0%SourceHy3 Preview—Not directly comparable
DRACO
Claude Opus 588.6%SourceHy3 Preview—Not directly comparable
BrowseComp (10-agent, prerelease)
Claude Opus 593.6%SourceHy3 Preview—Not directly comparable
OSWorld 2.0
Claude Opus 570.6%SourceHy3 Preview—Not directly comparable
MCP Atlas
Claude Opus 585.8%SourceHy3 Preview—Not directly comparable
MCP-Atlas claim coverage
Claude Opus 589.1%SourceHy3 Preview—Not directly comparable
LAB all-pass (Anthropic harness)
Claude Opus 523.58%SourceHy3 Preview—Not directly comparable
LAB criterion-pass (Anthropic harness)
Claude Opus 593.74%SourceHy3 Preview—Not directly comparable
LAB all-pass (Harvey held-out)
Claude Opus 511.7%SourceHy3 Preview—Not directly comparable
LAB criterion-pass (Harvey held-out)
Claude Opus 594.1%SourceHy3 Preview—Not directly comparable
Toolathlon-Verified
Claude Opus 580.6%SourceHy3 Preview—Not directly comparable
Toolathlon Verified Pass@3
Claude Opus 587.0%SourceHy3 Preview—Not directly comparable
Toolathlon Verified Pass³
Claude Opus 573.1%SourceHy3 Preview—Not directly comparable
Toolathlon Verified avg. turns
Claude Opus 523.5 turnsSourceHy3 Preview—Not directly comparable
AutomationBench
Claude Opus 526.0%SourceHy3 Preview—Not directly comparable
Terminal-Bench 2.1 (Vals)
Claude Opus 584.6%SourceHy3 Preview—Not directly comparable
Terminal-Bench 2.0
Claude Opus 5—Hy3 Preview54.4%SourceNot directly comparable
Gert Labs
Claude Opus 5—Hy3 Preview36.91%SourceNot directly comparable
Coding
Bug Hunt Bench
Claude Opus 527 fixesSourceHy3 Preview—Not directly comparable
SWE-bench Verified
Claude Opus 596%SourceHy3 Preview74.4%SourceClaude Opus 5 leads this result
SWE-bench Pro
Claude Opus 579.2%SourceHy3 Preview—Not directly comparable
SWE Multilingual
Claude Opus 589.5%SourceHy3 Preview—Not directly comparable
SWE Multimodal
Claude Opus 559.4%SourceHy3 Preview—Not directly comparable
deepSwe
Claude Opus 568.8%SourceHy3 Preview—Not directly comparable
FrontierCode 1.1 Main
Claude Opus 553.4%SourceHy3 Preview—Not directly comparable
FrontierCode 1.1 Extended
Claude Opus 563.6%SourceHy3 Preview—Not directly comparable
FrontierSWE v2
Claude Opus 552.0%SourceHy3 Preview—Not directly comparable
ProgramBench (episode 1)
Claude Opus 583.0%SourceHy3 Preview—Not directly comparable
ProgramBench
Claude Opus 593.0%SourceHy3 Preview—Not directly comparable
cursorBench32
Claude Opus 570.0%SourceHy3 Preview—Not directly comparable
VulcanBench v3
Claude Opus 587.0%SourceHy3 Preview—Not directly comparable
VulcanBench CII v1
Claude Opus 596.4%SourceHy3 Preview—Not directly comparable
LiveCodeBench (Vals)
Claude Opus 589.0%SourceHy3 Preview—Not directly comparable
SWE-bench (Vals)
Claude Opus 597.0%SourceHy3 Preview—Not directly comparable
Terminal-Bench 2.0
Claude Opus 5—Hy3 Preview54.4%SourceNot directly comparable
Reasoning
Knowledge
HLE
Claude Opus 564.7%SourceHy3 Preview—Not directly comparable
HLE w/o tools
Claude Opus 556.3%SourceHy3 Preview—Not directly comparable
HLE-Verified
Claude Opus 554.4%SourceHy3 Preview—Not directly comparable
LABBench2
Claude Opus 584.2%SourceHy3 Preview—Not directly comparable
HealthBench (raw)
Claude Opus 567.1%SourceHy3 Preview—Not directly comparable
HealthBench (length-adjusted)
Claude Opus 557.8%SourceHy3 Preview—Not directly comparable
HealthBench Professional
Claude Opus 559.8%SourceHy3 Preview—Not directly comparable
HealthBench Professional (raw)
Claude Opus 573.4%SourceHy3 Preview—Not directly comparable
BioMysteryBench (human-solvable)
Claude Opus 590.1%SourceHy3 Preview—Not directly comparable
BioMysteryBench (human-difficult)
Claude Opus 549.4%SourceHy3 Preview—Not directly comparable
SpatialBench Verified
Claude Opus 572.5%SourceHy3 Preview—Not directly comparable
SingleCellBench
Claude Opus 560.6%SourceHy3 Preview—Not directly comparable
ProteinGym Hard
Claude Opus 547.7%SourceHy3 Preview—Not directly comparable
Protein Design
Claude Opus 542.5%SourceHy3 Preview—Not directly comparable
Organic chemistry V2
Claude Opus 561.6%SourceHy3 Preview—Not directly comparable
Protocols (troubleshooting)
Claude Opus 561.1%SourceHy3 Preview—Not directly comparable
Protocols (understanding)
Claude Opus 578.4%SourceHy3 Preview—Not directly comparable
GPQA Diamond (Vals)
Claude Opus 593.4%SourceHy3 Preview—Not directly comparable
MMLU-Pro (Vals)
Claude Opus 591.6%SourceHy3 Preview—Not directly comparable
GPQA
Claude Opus 5—Hy3 Preview87.2%SourceNot directly comparable
GPQA-D
Claude Opus 5—Hy3 Preview87.2%SourceNot directly comparable
Math
IMO 2026
Claude Opus 542/42SourceHy3 Preview—Not directly comparable
RiemannBench (no tools)
Claude Opus 560.0%SourceHy3 Preview—Not directly comparable
RiemannBench (tools)
Claude Opus 579.0%SourceHy3 Preview—Not directly comparable
ArXivMath Jun. 2026 (no tools)
Claude Opus 590.8%SourceHy3 Preview—Not directly comparable
ArXivMath Jun. 2026 (tools)
Claude Opus 591.3%SourceHy3 Preview—Not directly comparable
Multilingual
Multimodal
Chartography (no tools)
Claude Opus 529.6%SourceHy3 Preview—Not directly comparable
Chartography (tools)
Claude Opus 583.0%SourceHy3 Preview—Not directly comparable
BenchCAD Vision2Code (no tools)
Claude Opus 50.366SourceHy3 Preview—Not directly comparable
BenchCAD Vision2Code (tools)
Claude Opus 50.821SourceHy3 Preview—Not directly comparable
GDP.pdf (no tools)
Claude Opus 583.4%SourceHy3 Preview—Not directly comparable
GDP.pdf (tools)
Claude Opus 585.5%SourceHy3 Preview—Not directly comparable
OfficeQA
Claude Opus 578.1%SourceHy3 Preview—Not directly comparable
OfficeQA Pro
Claude Opus 566.9%SourceHy3 Preview—Not directly comparable
Frequently asked questions
Which is better, Claude Opus 5 or Hy3 Preview?
Claude Opus 5 has the higher public score, 80.66 versus 57.08, and the 90% score intervals do not overlap. That is the clearest overall quality signal in the current public data.
Which is better for coding, Claude Opus 5 or Hy3 Preview?
Claude Opus 5 scores higher for coding on the public lane, 75.6 to 45.9. Hy3 Preview is scored on Estimated evidence for coding, so the reading is directional rather than like-for-like. BenchLM does not name a winner for coding from a directional reading; read the shared benchmark rows directly and test the models on the same task set.
Which is better for agentic tasks, Claude Opus 5 or Hy3 Preview?
Claude Opus 5 scores higher for agentic tasks on the public lane, 77.4 to 49.9. Hy3 Preview is scored on Estimated evidence for agentic tasks, so the reading is directional rather than like-for-like. BenchLM does not name a winner for agentic tasks from a directional reading; read the shared benchmark rows directly and test the models on the same task set.
Which costs less, Claude Opus 5 or Hy3 Preview?
Both models do not have comparable published API token rates, so this page does not name a universal price winner.
Which has the larger context window, Claude Opus 5 or Hy3 Preview?
Claude Opus 5 has the larger documented context window: 1M, compared with 256K.
Related comparisons
Last updated September 4, 2026
Watch Claude Opus 5 vs Hy3 Preview
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.