Model comparison
Claude Opus 5 vs Claude Sonnet 4.6
Head-to-head evidence from 14 shared benchmark results across 5 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: Claude Opus 5 #1 (Estimated); Claude Sonnet 4.6 #34 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. Claude Opus 5 and Claude Sonnet 4.6 share 14 comparable benchmark results. 4 of 8 categories are comparable. 65 results are unique to Claude Opus 5; 19 to Claude Sonnet 4.6.
Updated July 24, 2026- Shared results
- 14
- Claude Opus 5 only
- 65
- Claude Sonnet 4.6 only
- 19
- Comparable categories
- 4 / 8
Pick Claude Opus 5 if you want the stronger benchmark profile. Claude Sonnet 4.6 only becomes the better choice if multimodal & grounded is the priority or you want the cheaper token bill.
Confidence note. This is a partial-evidence comparison with 14 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 64.4. 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 agentic, where it averages 90.8 against 65.2. The single biggest benchmark swing on the page is SWE-bench Verified, 96% to 79.6%. Claude Sonnet 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 also the more expensive model on tokens at $5.00 input / $25.00 output per 1M tokens, versus $3.00 input / $15.00 output per 1M tokens for Claude Sonnet 4.6. Claude Opus 5 is the reasoning model in the pair, while Claude Sonnet 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 5 | Δ | Claude Sonnet 4.6 |
|---|---|---|---|
| Agentic | Claude Opus 590.8 | Margin← 25.6 | Claude Sonnet 4.665.2 |
| Coding | Claude Opus 589.5 | Margin← 20.4 | Claude Sonnet 4.669.1 |
| Multimodal | Claude Opus 566.9 | Margin→ 10.5 | Claude Sonnet 4.677.4 |
| Knowledge | Claude Opus 564.7 | Margin→ 1.3 | Claude Sonnet 4.666.0 |
| Reasoning | Claude Opus 590.4 | MarginNo overlap | Claude Sonnet 4.6Not measured |
| Math | Claude Opus 5Not measured | MarginNo overlap | Claude Sonnet 4.626.4 |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
SWE-bench Verified
CodingA 96%B 79.6%Winner: Claude Opus 5Δ 16.4SWE-bench Verified: Claude Opus 5 scored 96%; Claude Sonnet 4.6 scored 79.6%. Claude Opus 5 wins this benchmark. - Source ↗
HLE
KnowledgeA 64.7%B 49%Winner: Claude Opus 5Δ 15.7HLE: Claude Opus 5 scored 64.7%; Claude Sonnet 4.6 scored 49%. 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 5 | Claude Sonnet 4.6 | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | Claude Opus 5$5 input / $25 output | Claude Sonnet 4.6$3 input / $15 output | Claude Sonnet 4.6 has the lower combined listed price. |
| Generation speedtokens per second | Claude Opus 5Not available | Claude Sonnet 4.644 tok/s | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | Claude Opus 5Not available | Claude Sonnet 4.61.48 s | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | Claude Opus 5Not available | Claude Sonnet 4.6200K | A complete context comparison is not available. |
Benchmark Deep Dive
AgenticClaude Opus 5 wins31 benchmarks
| Benchmark | Claude Opus 5 | Claude Sonnet 4.6 | Result |
|---|---|---|---|
| FrontierBench v0.1Source | 43.3% | — | Not comparable |
| BrowseCompSource | 90.8% | — | Not comparable |
| HLE w/ toolsSource | 64.7% | — | Not comparable |
| DeepSearchQASource | 95.0% | — | Not comparable |
| DRACOSource | 88.6% | — | Not comparable |
| BrowseComp (10-agent, prerelease)Source | 93.6% | — | Not comparable |
| OSWorld 2.0Source | 70.6% | 8.3% | Claude Opus 5 leads |
| 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 |
| Terminal-Bench 2.0Source | — | 59.1% | Not comparable |
| OSWorld-VerifiedSource | — | 72.1% | Not comparable |
| Claw-EvalSource | — | 67.8% | Not comparable |
| CyberGymSource | — | 65.2% | Not comparable |
| τ²-bench resultsSource | — | 79.5% | Not comparable |
| Gert LabsSource | — | 62.92% | Not comparable |
| JobBenchSource | — | 36.9% | Not comparable |
CodingClaude Opus 5 wins16 benchmarks
| Benchmark | Claude Opus 5 | Claude Sonnet 4.6 | Result |
|---|---|---|---|
| SWE-bench VerifiedSource | 96% | 79.6% | Claude Opus 5 leads |
| SWE-bench ProSource | 79.2% | — | Not comparable |
| SWE MultilingualSource | 89.5% | — | Not comparable |
| SWE MultimodalSource | 59.4% | — | Not comparable |
| deepSweSource | 68.8% | — | Not comparable |
| FrontierCode 1.1 MainSource | 53.4% | 24.3% | Claude Opus 5 leads |
| 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 |
| AA-SciCodeSource | 55.7% | 46.9% | Claude Opus 5 leads |
| SWE-RebenchSource | — | 60.7% | Not comparable |
| React Native EvalsSource | — | 80.6% | Not comparable |
| Vibe Code BenchSource | — | 51.48% | Not comparable |
| cursorBench31Source | — | 48.8% | Not comparable |
Reasoning5 benchmarks
KnowledgeClaude Sonnet 4.6 wins24 benchmarks
| Benchmark | Claude Opus 5 | Claude Sonnet 4.6 | Result |
|---|---|---|---|
| HLESource | 64.7% | 49% | Claude Opus 5 leads |
| HLE w/o toolsSource | 56.3% | — | Not comparable |
| 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 |
| Artificial Analysis Intelligence IndexSource | 60.7% | 35.9% | Claude Opus 5 leads |
| AA-GPQA DiamondSource | 93.2% | 79.9% | Claude Opus 5 leads |
| AA-HLESource | 52.6% | 13.2% | Claude Opus 5 leads |
| AA-Omniscience IndexSource | 31.3% | -2.9% | Claude Opus 5 leads |
| AA-Omniscience AccuracySource | 54.2% | 38.0% | Claude Opus 5 leads |
| AA-Omniscience Hallucination RateSource | 50.1% | 65.9% | Claude Opus 5 leads |
| GPQASource | — | 89.9% | Not comparable |
| SuperGPQASource | — | 95% | Not comparable |
| MMLU-ProSource | — | 79.2% | Not comparable |
Math7 benchmarks
| Benchmark | Claude Opus 5 | Claude Sonnet 4.6 | Result |
|---|---|---|---|
| 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 |
| FrontierMath v2 (Tiers 1-3)Source | — | 32.400% | Not comparable |
| FrontierMath v2 (Tier 4)Source | — | 8.300% | Not comparable |
Multilingual3 benchmarks
MultimodalClaude Sonnet 4.6 wins11 benchmarks
| Benchmark | Claude Opus 5 | Claude Sonnet 4.6 | Result |
|---|---|---|---|
| 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 |
| AA-MMMU-ProSource | 84.7% | 70.6% | Claude Opus 5 leads |
| CharXivSource | — | 77.4% | Not comparable |
| Design Arena WebsiteSource | — | 1314 | Not comparable |
Inst. Following1 benchmarks
| Benchmark | Claude Opus 5 | Claude Sonnet 4.6 | Result |
|---|---|---|---|
| AA-IFBenchSource | — | 41.2% | Not comparable |
Frequently Asked Questions (5)
Which is better, Claude Opus 5 or Claude Sonnet 4.6?
Claude Opus 5 is ahead on BenchLM's BenchAlign leaderboard, 85.88 to 64.4. The biggest single separator in this matchup is SWE-bench Verified, where the scores are 96% and 79.6%.
Which is better for knowledge tasks, Claude Opus 5 or Claude Sonnet 4.6?
Claude Sonnet 4.6 has the edge for knowledge tasks in this comparison, averaging 66 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 5 or Claude Sonnet 4.6?
Claude Opus 5 has the edge for coding in this comparison, averaging 89.5 versus 69.1. 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 5 or Claude Sonnet 4.6?
Claude Opus 5 has the edge for agentic tasks in this comparison, averaging 90.8 versus 65.2. Inside this category, OSWorld 2.0 is the benchmark that creates the most daylight between them.
Which is better for multimodal and grounded tasks, Claude Opus 5 or Claude Sonnet 4.6?
Claude Sonnet 4.6 has the edge for multimodal and grounded tasks in this comparison, averaging 77.4 versus 66.9. Inside this category, AA-MMMU-Pro is the benchmark that creates the most daylight between them.