Agentic
Like-for-like- Claude Haiku 4.5
- 27.0
- Supported · #143/151
- Claude Opus 5
- 77.4
- Supported · #2/151
- Basis
- BenchAlign lane · 2 vs 19 public rows
- Reading
- Claude Opus 5 leads
Claude Haiku 4.5 vs Claude Opus 5
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 52.73, and the 90% score intervals do not overlap.
7 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.
Coding work
Code generation, repair, and software-engineering tasks
Claude Opus 5
Claude Opus 5 leads on the public coding lane, 75.6 to 27.3, with Supported evidence for both models and non-overlapping 90% intervals.
Confidence: stronger
Agentic work
Tool use, computer use, and multi-step task completion
Claude Opus 5
Claude Opus 5 leads on the public agentic lane, 77.4 to 27, with Supported evidence for both models and non-overlapping 90% intervals.
Confidence: stronger
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
Chat turn cost
1K fresh input + 500 output tokens
Claude Haiku 4.5
Claude Haiku 4.5 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-rates
Repository review cost
50K fresh input + 3K output tokens
Claude Haiku 4.5
Claude Haiku 4.5 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-rates
Cache-heavy agent loop cost
200K cached + 20K fresh input + 10K output tokens
Not enough matched evidence
The page does not recommend a cost winner because at least one model cannot fit the stated workload in one request. Claude Haiku 4.5 does not fit this workload in one request.
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.
3 Claude Haiku 4.5 only
7 Shared
66 Claude Opus 5 only
- Shared results
- 7
- Claude Haiku 4.5 only
- 3
- Claude Opus 5 only
- 66
- Like-for-like categories
- 2 / 8
1 category rests 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
Like-for-like- Claude Haiku 4.5
- 27.3
- Supported · #173/183
- Claude Opus 5
- 75.6
- Supported · #3/183
- Basis
- BenchAlign lane · 4 vs 16 public rows
- Reading
- Claude Opus 5 leads
Knowledge
Directional only- Claude Haiku 4.5
- 44.6
- Estimated · #117/181
- Claude Opus 5
- 82.1
- Supported · #3/181
- Basis
- BenchAlign lane · 2 vs 19 public rows
- Reading
- Directional only
Reasoning
Not comparable- Claude Haiku 4.5
- Not ranked
- Claude Opus 5
- 75.6
- #13/22
- Basis
- Provisional lane · 0 vs 2 weighted rows
- Reading
- Not comparable
Math
Not comparable- Claude Haiku 4.5
- 28.9
- Unranked · 2 rankable rows
- Claude Opus 5
- Not ranked
- Basis
- Provisional lane · 2 vs 0 weighted rows
- Reading
- Not comparable
Multilingual
Not comparable- Claude Haiku 4.5
- Not ranked
- Claude Opus 5
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Multimodal
Not comparable- Claude Haiku 4.5
- Not ranked
- Claude Opus 5
- 88.7
- #2/48
- Basis
- Provisional lane · 0 vs 1 weighted rows
- Reading
- Not comparable
Instruction following
Not comparable- Claude Haiku 4.5
- Not ranked
- Claude Opus 5
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
| Category | Claude Haiku 4.5 | Claude Opus 5 | Basis | Reading |
|---|---|---|---|---|
| Agentic | 27.0Supported · #143/151 | 77.4Supported · #2/151 | Like-for-likeBenchAlign lane · 2 vs 19 public rows | Claude Opus 5 leads |
| Coding | 27.3Supported · #173/183 | 75.6Supported · #3/183 | Like-for-likeBenchAlign lane · 4 vs 16 public rows | Claude Opus 5 leads |
| Knowledge | 44.6Estimated · #117/181 | 82.1Supported · #3/181 | Directional onlyBenchAlign lane · 2 vs 19 public rows | Directional only |
| Reasoning | Not ranked | 75.6#13/22 | Not comparableProvisional lane · 0 vs 2 weighted rows | Not comparable |
| Math | 28.9Unranked · 2 rankable rows | Not ranked | Not comparableProvisional lane · 2 vs 0 weighted rows | Not comparable |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Multimodal | Not ranked | 88.7#2/48 | Not comparableProvisional lane · 0 vs 1 weighted rows | Not comparable |
| Instruction following | Not ranked | Not ranked | 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.
LiveCodeBench (Vals)
Coding
Claude Haiku 4.5: 41.2%Claude Opus 5: 89.0%Normalized gap 47.8Claude Haiku 4.5 source Claude Opus 5 sourceSWE-bench Verified
Coding
Claude Haiku 4.5: 73.3%Claude Opus 5: 96%Normalized gap 22.7Claude Haiku 4.5 source Claude Opus 5 sourceMMLU-Pro (Vals)
Knowledge
Claude Haiku 4.5: 78.7%Claude Opus 5: 91.6%Normalized gap 12.9Claude Haiku 4.5 source Claude Opus 5 source
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 Haiku 4.5
- $0.0035
- Fits in one request
- Claude Opus 5
- $0.0175
- Fits in one request
Claude Haiku 4.5 has the lower modeled cost
Costs use the listed standard API rates.
Repository review
50K fresh input + 3K output tokens
- Claude Haiku 4.5
- $0.065
- Fits in one request
- Claude Opus 5
- $0.325
- Fits in one request
Claude Haiku 4.5 has the lower modeled cost
Costs use the listed standard API rates.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- Claude Haiku 4.5
- $0.09
- Does not fit in one request
- Claude Opus 5
- $0.45
- Fits in one request
Claude Haiku 4.5 does not fit this workload in one request.
Specification differences
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
SpecificationClaude Haiku 4.5Claude Opus 5
Context window
Maximum documented context; output-token limits may be lower.
Claude Haiku 4.5
Claude Opus 5
API model ID
Claude Haiku 4.5
claude-haiku-4-5-20251001
Claude API pricingClaude Opus 5
claude-opus-5
Anthropic model overviewCached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Claude Haiku 4.5
$0.1 per 1M cached input tokens
Claude API pricingClaude Opus 5
$0.5 per 1M cached input tokens
Claude API pricingDocumented inputs
Claude Haiku 4.5
Not sourced
Claude Opus 5
text, image
Anthropic model overviewDocumented outputs
Claude Haiku 4.5
Not sourced
Claude Opus 5
Provider availability
Claude Haiku 4.5
Not sourced
Claude Opus 5
Generally Available · Claude API
Anthropic model overviewReasoning profile
Claude Haiku 4.5
Non-Reasoning
Claude Opus 5
Reasoning
Weight access
Claude Haiku 4.5
Proprietary
Claude Opus 5
Proprietary
License
Claude Haiku 4.5
Proprietary
Claude Opus 5
Proprietary
Release date
Claude Haiku 4.5
2025-10-15
Claude Opus 5
2026-07-24
If you already use one of these models
- Deployment change
- Both entries list Anthropic as the provider. Confirm endpoint, model ID, limits, and feature support before switching.
- Quality signal
- Claude Opus 5 has the higher public score, 80.66 versus 52.73, and the 90% score intervals do not overlap.
- Workload cost
- Repository review: $0.065 vs $0.325. Cache-heavy agent loop: $0.09 vs $0.45.
- 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 evidence76 rows
Agentic
JobBench
Claude Haiku 4.516.0%SourceClaude Opus 5—Not directly comparable
Terminal-Bench 2.1 (Vals)
Claude Haiku 4.543.8%SourceClaude Opus 584.6%SourceClaude Opus 5 leads this result
Terminal-Bench 3.0
Claude Haiku 4.5—Claude Opus 542.7%SourceNot directly comparable
BrowseComp
Claude Haiku 4.5—Claude Opus 590.8%SourceNot directly comparable
HLE w/ tools
Claude Haiku 4.5—Claude Opus 564.7%SourceNot directly comparable
DeepSearchQA
Claude Haiku 4.5—Claude Opus 595.0%SourceNot directly comparable
DRACO
Claude Haiku 4.5—Claude Opus 588.6%SourceNot directly comparable
BrowseComp (10-agent, prerelease)
Claude Haiku 4.5—Claude Opus 593.6%SourceNot directly comparable
OSWorld 2.0
Claude Haiku 4.5—Claude Opus 570.6%SourceNot directly comparable
MCP Atlas
Claude Haiku 4.5—Claude Opus 585.8%SourceNot directly comparable
MCP-Atlas claim coverage
Claude Haiku 4.5—Claude Opus 589.1%SourceNot directly comparable
LAB all-pass (Anthropic harness)
Claude Haiku 4.5—Claude Opus 523.58%SourceNot directly comparable
LAB criterion-pass (Anthropic harness)
Claude Haiku 4.5—Claude Opus 593.74%SourceNot directly comparable
LAB all-pass (Harvey held-out)
Claude Haiku 4.5—Claude Opus 511.7%SourceNot directly comparable
LAB criterion-pass (Harvey held-out)
Claude Haiku 4.5—Claude Opus 594.1%SourceNot directly comparable
Toolathlon-Verified
Claude Haiku 4.5—Claude Opus 580.6%SourceNot directly comparable
Toolathlon Verified Pass@3
Claude Haiku 4.5—Claude Opus 587.0%SourceNot directly comparable
Toolathlon Verified Pass³
Claude Haiku 4.5—Claude Opus 573.1%SourceNot directly comparable
Toolathlon Verified avg. turns
Claude Haiku 4.5—Claude Opus 523.5 turnsSourceNot directly comparable
AutomationBench
Claude Haiku 4.5—Claude Opus 526.0%SourceNot directly comparable
Coding
SWE-bench Verified
Claude Haiku 4.573.3%SourceClaude Opus 596%SourceClaude Opus 5 leads this result
VulcanBench v3
Claude Haiku 4.576.2%SourceClaude Opus 587.0%SourceClaude Opus 5 leads this result
LiveCodeBench (Vals)
Claude Haiku 4.541.2%SourceClaude Opus 589.0%SourceClaude Opus 5 leads this result
SWE-bench (Vals)
Claude Haiku 4.566.6%SourceClaude Opus 597.0%SourceClaude Opus 5 leads this result
Bug Hunt Bench
Claude Haiku 4.5—Claude Opus 527 fixesSourceNot directly comparable
SWE-bench Pro
Claude Haiku 4.5—Claude Opus 579.2%SourceNot directly comparable
SWE Multilingual
Claude Haiku 4.5—Claude Opus 589.5%SourceNot directly comparable
SWE Multimodal
Claude Haiku 4.5—Claude Opus 559.4%SourceNot directly comparable
deepSwe
Claude Haiku 4.5—Claude Opus 568.8%SourceNot directly comparable
FrontierCode 1.1 Main
Claude Haiku 4.5—Claude Opus 553.4%SourceNot directly comparable
FrontierCode 1.1 Extended
Claude Haiku 4.5—Claude Opus 563.6%SourceNot directly comparable
FrontierSWE v2
Claude Haiku 4.5—Claude Opus 552.0%SourceNot directly comparable
ProgramBench (episode 1)
Claude Haiku 4.5—Claude Opus 583.0%SourceNot directly comparable
ProgramBench
Claude Haiku 4.5—Claude Opus 593.0%SourceNot directly comparable
cursorBench32
Claude Haiku 4.5—Claude Opus 570.0%SourceNot directly comparable
VulcanBench CII v1
Claude Haiku 4.5—Claude Opus 596.4%SourceNot directly comparable
Reasoning
Knowledge
GPQA Diamond (Vals)
Claude Haiku 4.572.2%SourceClaude Opus 593.4%SourceClaude Opus 5 leads this result
MMLU-Pro (Vals)
Claude Haiku 4.578.7%SourceClaude Opus 591.6%SourceClaude Opus 5 leads this result
HLE
Claude Haiku 4.5—Claude Opus 564.7%SourceNot directly comparable
HLE w/o tools
Claude Haiku 4.5—Claude Opus 556.3%SourceNot directly comparable
HLE-Verified
Claude Haiku 4.5—Claude Opus 554.4%SourceNot directly comparable
LABBench2
Claude Haiku 4.5—Claude Opus 584.2%SourceNot directly comparable
HealthBench (raw)
Claude Haiku 4.5—Claude Opus 567.1%SourceNot directly comparable
HealthBench (length-adjusted)
Claude Haiku 4.5—Claude Opus 557.8%SourceNot directly comparable
HealthBench Professional
Claude Haiku 4.5—Claude Opus 559.8%SourceNot directly comparable
HealthBench Professional (raw)
Claude Haiku 4.5—Claude Opus 573.4%SourceNot directly comparable
BioMysteryBench (human-solvable)
Claude Haiku 4.5—Claude Opus 590.1%SourceNot directly comparable
BioMysteryBench (human-difficult)
Claude Haiku 4.5—Claude Opus 549.4%SourceNot directly comparable
SpatialBench Verified
Claude Haiku 4.5—Claude Opus 572.5%SourceNot directly comparable
SingleCellBench
Claude Haiku 4.5—Claude Opus 560.6%SourceNot directly comparable
ProteinGym Hard
Claude Haiku 4.5—Claude Opus 547.7%SourceNot directly comparable
Protein Design
Claude Haiku 4.5—Claude Opus 542.5%SourceNot directly comparable
Organic chemistry V2
Claude Haiku 4.5—Claude Opus 561.6%SourceNot directly comparable
Protocols (troubleshooting)
Claude Haiku 4.5—Claude Opus 561.1%SourceNot directly comparable
Protocols (understanding)
Claude Haiku 4.5—Claude Opus 578.4%SourceNot directly comparable
Math
FrontierMath v2 (Tiers 1-3)
Claude Haiku 4.55.903%SourceClaude Opus 5—Not directly comparable
FrontierMath v2 (Tier 4)
Claude Haiku 4.52.083%SourceClaude Opus 5—Not directly comparable
IMO 2026
Claude Haiku 4.5—Claude Opus 542/42SourceNot directly comparable
RiemannBench (no tools)
Claude Haiku 4.5—Claude Opus 560.0%SourceNot directly comparable
RiemannBench (tools)
Claude Haiku 4.5—Claude Opus 579.0%SourceNot directly comparable
ArXivMath Jun. 2026 (no tools)
Claude Haiku 4.5—Claude Opus 590.8%SourceNot directly comparable
ArXivMath Jun. 2026 (tools)
Claude Haiku 4.5—Claude Opus 591.3%SourceNot directly comparable
Multilingual
Multimodal
Chartography (no tools)
Claude Haiku 4.5—Claude Opus 529.6%SourceNot directly comparable
Chartography (tools)
Claude Haiku 4.5—Claude Opus 583.0%SourceNot directly comparable
BenchCAD Vision2Code (no tools)
Claude Haiku 4.5—Claude Opus 50.366SourceNot directly comparable
BenchCAD Vision2Code (tools)
Claude Haiku 4.5—Claude Opus 50.821SourceNot directly comparable
GDP.pdf (no tools)
Claude Haiku 4.5—Claude Opus 583.4%SourceNot directly comparable
GDP.pdf (tools)
Claude Haiku 4.5—Claude Opus 585.5%SourceNot directly comparable
OfficeQA
Claude Haiku 4.5—Claude Opus 578.1%SourceNot directly comparable
OfficeQA Pro
Claude Haiku 4.5—Claude Opus 566.9%SourceNot directly comparable
Frequently asked questions
Which is better, Claude Haiku 4.5 or Claude Opus 5?
Claude Opus 5 has the higher public score, 80.66 versus 52.73, 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 Haiku 4.5 or Claude Opus 5?
Claude Opus 5 leads the public coding lane, 75.6 to 27.3, with Supported evidence for both models and non-overlapping 90% intervals.
Which is better for agentic tasks, Claude Haiku 4.5 or Claude Opus 5?
Claude Opus 5 leads the public agentic tasks lane, 77.4 to 27, with Supported evidence for both models and non-overlapping 90% intervals.
Which costs less, Claude Haiku 4.5 or Claude Opus 5?
For the stated presets, chat costs $0.0035 on Claude Haiku 4.5 and $0.0175 on Claude Opus 5; repository review costs $0.065 and $0.325; the cache-heavy agent loop costs $0.09 and $0.45. Claude Haiku 4.5 does not fit this workload in one request.
Which has the larger context window, Claude Haiku 4.5 or Claude Opus 5?
Claude Opus 5 has the larger documented context window: 1M, compared with 200K.
Related comparisons
Last updated September 4, 2026
Watch Claude Haiku 4.5 vs Claude Opus 5
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.