Model comparison
Claude Opus 4.6 vs Claude Opus 5
Head-to-head evidence from 17 shared benchmark results across 5 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: Claude Opus 4.6 #19 (Supported); Claude Opus 5 #1 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. Claude Opus 4.6 and Claude Opus 5 share 17 comparable benchmark results. 4 of 8 categories are comparable. 29 results are unique to Claude Opus 4.6; 62 to Claude Opus 5.
Updated July 24, 2026- Shared results
- 17
- Claude Opus 4.6 only
- 29
- Claude Opus 5 only
- 62
- Comparable categories
- 4 / 8
Pick Claude Opus 5 if you want the stronger benchmark profile. Claude Opus 4.6 only becomes the better choice if multimodal & grounded is the priority or you would rather avoid the extra latency and token burn of a reasoning model.
Confidence note. This is a partial-evidence comparison with 17 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 5 is clearly ahead on the BenchAlign aggregate, 85.88 to 67.84. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Claude Opus 5's sharpest advantage is in coding, where it averages 89.5 against 68.1. The single biggest benchmark swing on the page is SWE-bench Pro, 53.4% to 79.2%. Claude Opus 4.6 does hit back in multimodal & grounded, so the answer changes if that is the part of the workload you care about most.
Claude Opus 5 is the reasoning model in the pair, while Claude Opus 4.6 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.
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 | Claude Opus 4.6 | Δ | Claude Opus 5 |
|---|---|---|---|
| Coding | Claude Opus 4.668.1 | Margin→ 21.4 | Claude Opus 589.5 |
| Agentic | Claude Opus 4.673.0 | Margin→ 17.8 | Claude Opus 590.8 |
| Multimodal | Claude Opus 4.677.3 | Margin← 10.4 | Claude Opus 566.9 |
| Knowledge | Claude Opus 4.669.1 | Margin← 4.4 | Claude Opus 564.7 |
| Reasoning | Claude Opus 4.6Not measured | MarginNo overlap | Claude Opus 590.4 |
| Math | Claude Opus 4.636.3 | MarginNo overlap | Claude Opus 5Not measured |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
SWE-bench Pro
CodingA 53.4%B 79.2%Winner: Claude Opus 5Δ 25.8SWE-bench Pro: Claude Opus 4.6 scored 53.4%; Claude Opus 5 scored 79.2%. Claude Opus 5 wins this benchmark. - Source ↗
SWE-bench Verified
CodingA 80.8%B 96%Winner: Claude Opus 5Δ 15.2SWE-bench Verified: Claude Opus 4.6 scored 80.8%; Claude Opus 5 scored 96%. Claude Opus 5 wins this benchmark. - Source ↗
HLE
KnowledgeA 53%B 64.7%Winner: Claude Opus 5Δ 11.7HLE: Claude Opus 4.6 scored 53%; Claude Opus 5 scored 64.7%. Claude Opus 5 wins this benchmark. - Source ↗
BrowseComp
AgenticA 83.7%B 90.8%Winner: Claude Opus 5Δ 7.1BrowseComp: Claude Opus 4.6 scored 83.7%; Claude Opus 5 scored 90.8%. Claude Opus 5 wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | Claude Opus 4.6 | Claude Opus 5 | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | Claude Opus 4.6$5 input / $25 output | Claude Opus 5$5 input / $25 output | Listed prices are equal. |
| Generation speedtokens per second | Claude Opus 4.640 tok/s | Claude Opus 5Not available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | Claude Opus 4.61.78 s | Claude Opus 5Not available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | Claude Opus 4.61M | Claude Opus 5Not available | A complete context comparison is not available. |
Benchmark Deep Dive
AgenticClaude Opus 5 wins32 benchmarks
| Benchmark | Claude Opus 4.6 | Claude Opus 5 | Result |
|---|---|---|---|
| Terminal-Bench 2.0Source | 65.4% | — | Not comparable |
| BrowseCompSource | 83.7% | 90.8% | Claude Opus 5 leads |
| OSWorld-VerifiedSource | 72.7% | — | Not comparable |
| τ²-bench resultsSource | 84.8% | — | Not comparable |
| Claw-EvalSource | 70.4% | — | Not comparable |
| DeepSearchQASource | 73.7% | 95.0% | Claude Opus 5 leads |
| CyberGymSource | 66.6% | — | Not comparable |
| Gert LabsSource | 61.85% | — | Not comparable |
| ResearchClawBenchSource | 19.9% | — | Not comparable |
| JobBenchSource | 36.7% | — | Not comparable |
| FrontierBench v0.1Source | — | 43.3% | Not comparable |
| HLE w/ toolsSource | — | 64.7% | Not comparable |
| DRACOSource | — | 88.6% | Not comparable |
| BrowseComp (10-agent, prerelease)Source | — | 93.6% | Not comparable |
| OSWorld 2.0Source | — | 70.6% | Not comparable |
| MCP AtlasSource | — | 85.8% | Not comparable |
| MCP-Atlas claim coverageSource | — | 89.1% | Not comparable |
| LAB all-pass (Anthropic harness)Source | — | 23.58% | Not comparable |
| LAB criterion-pass (Anthropic harness)Source | — | 93.74% | Not comparable |
| LAB all-pass (Harvey held-out)Source | — | 11.7% | Not comparable |
| LAB criterion-pass (Harvey held-out)Source | — | 94.1% | Not comparable |
| GDPval-AASource | — | 1861 | Not comparable |
| Toolathlon-VerifiedSource | — | 80.6% | Not comparable |
| Toolathlon Verified Pass@3Source | — | 87.0% | Not comparable |
| Toolathlon Verified Pass³Source | — | 73.1% | Not comparable |
| Toolathlon Verified avg. turnsSource | — | 23.5 turns | Not comparable |
| AutomationBenchSource | — | 26.0% | Not comparable |
| AA Agentic IndexSource | — | 55.3% | Not comparable |
| GDPval-AASource | — | 68.0% | Not comparable |
| AA Tau3 BankingSource | — | 30.3% | Not comparable |
| AA BriefcaseSource | — | 1720 | Not comparable |
| aaTerminalBench21Source | — | 89.1% | Not comparable |
CodingClaude Opus 5 wins17 benchmarks
| Benchmark | Claude Opus 4.6 | Claude Opus 5 | Result |
|---|---|---|---|
| SWE-bench VerifiedSource | 80.8% | 96% | Claude Opus 5 leads |
| SWE-bench Verified*Source | 75.6% | — | Not comparable |
| LiveCodeBench ProSource | 70.7% | — | Not comparable |
| SWE-bench ProSource | 53.4% | 79.2% | Claude Opus 5 leads |
| SWE-RebenchSource | 65.3% | — | Not comparable |
| React Native EvalsSource | 84.1% | — | Not comparable |
| Vibe Code BenchSource | 57.57% | — | Not comparable |
| AA-SciCodeSource | 45.7% | 55.7% | Claude Opus 5 leads |
| FrontierCode 1.1 MainSource | 26.9% | 53.4% | Claude Opus 5 leads |
| SWE MultilingualSource | — | 89.5% | Not comparable |
| SWE MultimodalSource | — | 59.4% | Not comparable |
| deepSweSource | — | 68.8% | Not comparable |
| FrontierCode 1.1 ExtendedSource | — | 63.6% | Not comparable |
| ProgramBench (episode 1)Source | — | 83.0% | Not comparable |
| ProgramBenchSource | — | 93.0% | Not comparable |
| cursorBench32Source | — | 70.0% | Not comparable |
| AA Coding IndexSource | — | 78.0% | Not comparable |
Reasoning5 benchmarks
KnowledgeClaude Opus 4.6 wins28 benchmarks
| Benchmark | Claude Opus 4.6 | Claude Opus 5 | Result |
|---|---|---|---|
| GPQASource | 91.3% | — | Not comparable |
| GPQA-DSource | 89.2% | — | Not comparable |
| SuperGPQASource | 95% | — | Not comparable |
| MMLU-ProSource | 82% | — | Not comparable |
| MMLU-Pro (Arcee)Source | 89.1% | — | Not comparable |
| HLESource | 53% | 64.7% | Claude Opus 5 leads |
| HLE w/o toolsSource | 40% | 56.3% | Claude Opus 5 leads |
| HealthBench HardSource | 14.8% | — | Not comparable |
| MedXpertQA (Text)Source | 52.1% | — | Not comparable |
| Artificial Analysis Intelligence IndexSource | 37.8% | 60.7% | Claude Opus 5 leads |
| AA-GPQA DiamondSource | 84.0% | 93.2% | Claude Opus 5 leads |
| AA-HLESource | 18.6% | 52.6% | Claude Opus 5 leads |
| AA-Omniscience IndexSource | 3.5% | 31.3% | Claude Opus 5 leads |
| AA-Omniscience AccuracySource | 45.2% | 54.2% | Claude Opus 5 leads |
| AA-Omniscience Hallucination RateSource | 76.0% | 50.1% | Claude Opus 5 leads |
| HealthBench (raw)Source | — | 67.1% | Not comparable |
| HealthBench (length-adjusted)Source | — | 57.8% | Not comparable |
| HealthBench ProfessionalSource | — | 59.8% | Not comparable |
| HealthBench Professional (raw)Source | — | 73.4% | Not comparable |
| BioMysteryBench (human-solvable)Source | — | 90.1% | Not comparable |
| BioMysteryBench (human-difficult)Source | — | 49.4% | Not comparable |
| SpatialBench VerifiedSource | — | 72.5% | Not comparable |
| SingleCellBenchSource | — | 60.6% | Not comparable |
| ProteinGym HardSource | — | 47.7% | Not comparable |
| Protein DesignSource | — | 42.5% | Not comparable |
| Organic chemistry V2Source | — | 61.6% | Not comparable |
| Protocols (troubleshooting)Source | — | 61.1% | Not comparable |
| Protocols (understanding)Source | — | 78.4% | Not comparable |
Math8 benchmarks
| Benchmark | Claude Opus 4.6 | Claude Opus 5 | Result |
|---|---|---|---|
| AIME25 (Arcee)Source | 99.8% | — | Not comparable |
| FrontierMath v2 (Tiers 1-3)Source | 40.700% | — | Not comparable |
| FrontierMath v2 (Tier 4)Source | 22.900% | — | Not comparable |
| IMO 2026Source | — | 42/42 | Not comparable |
| RiemannBench (no tools)Source | — | 60.0% | Not comparable |
| RiemannBench (tools)Source | — | 79.0% | Not comparable |
| ArXivMath Jun. 2026 (no tools)Source | — | 90.8% | Not comparable |
| ArXivMath Jun. 2026 (tools)Source | — | 91.3% | Not comparable |
Multilingual3 benchmarks
MultimodalClaude Opus 4.6 wins14 benchmarks
| Benchmark | Claude Opus 4.6 | Claude Opus 5 | Result |
|---|---|---|---|
| MMMU-ProSource | 77.3% | — | Not comparable |
| ERQASource | 51.6% | — | Not comparable |
| ScreenSpot ProSource | 83.1% | — | Not comparable |
| MedXpertQA (MM)Source | 64.8% | — | Not comparable |
| AA-MMMU-ProSource | 72.5% | 84.7% | Claude Opus 5 leads |
| Design Arena WebsiteSource | 1325 | — | Not comparable |
| Chartography (no tools)Source | — | 29.6% | Not comparable |
| Chartography (tools)Source | — | 83.0% | Not comparable |
| BenchCAD Vision2Code (no tools)Source | — | 0.366 | Not comparable |
| BenchCAD Vision2Code (tools)Source | — | 0.821 | Not comparable |
| GDP.pdf (no tools)Source | — | 83.4% | Not comparable |
| GDP.pdf (tools)Source | — | 85.5% | Not comparable |
| OfficeQASource | — | 78.1% | Not comparable |
| OfficeQA ProSource | — | 66.9% | Not comparable |
Inst. Following1 benchmarks
| Benchmark | Claude Opus 4.6 | Claude Opus 5 | Result |
|---|---|---|---|
| AA-IFBenchSource | 44.6% | — | Not comparable |
Frequently Asked Questions (5)
Which is better, Claude Opus 4.6 or Claude Opus 5?
Claude Opus 5 is ahead on BenchLM's BenchAlign leaderboard, 85.88 to 67.84. The biggest single separator in this matchup is SWE-bench Pro, where the scores are 53.4% and 79.2%.
Which is better for knowledge tasks, Claude Opus 4.6 or Claude Opus 5?
Claude Opus 4.6 has the edge for knowledge tasks in this comparison, averaging 69.1 versus 64.7. Inside this category, AA-HLE is the benchmark that creates the most daylight between them.
Which is better for coding, Claude Opus 4.6 or Claude Opus 5?
Claude Opus 5 has the edge for coding in this comparison, averaging 89.5 versus 68.1. Inside this category, FrontierCode 1.1 Main is the benchmark that creates the most daylight between them.
Which is better for agentic tasks, Claude Opus 4.6 or Claude Opus 5?
Claude Opus 5 has the edge for agentic tasks in this comparison, averaging 90.8 versus 73. Inside this category, DeepSearchQA is the benchmark that creates the most daylight between them.
Which is better for multimodal and grounded tasks, Claude Opus 4.6 or Claude Opus 5?
Claude Opus 4.6 has the edge for multimodal and grounded tasks in this comparison, averaging 77.3 versus 66.9. Inside this category, AA-MMMU-Pro is the benchmark that creates the most daylight between them.