# Claude Opus 4.7 vs Claude Sonnet 5

> Side-by-side benchmark comparison for Claude Opus 4.7 and Claude Sonnet 5 across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/claude-opus-4-7-vs-claude-sonnet-5
- Last updated: September 21, 2026

- Shared sourced benchmarks: 7
- HTML indexing: indexable
- Ranking lane: BenchAlign v5

## Quick Verdict

Pick Claude Opus 4.7 if you want the stronger benchmark profile. Claude Sonnet 5 only makes more sense when its price, context window, or workload-specific category wins matter more than the overall score.

## Summary

- Claude Opus 4.7 leads overall 70.94 to 69.62.
- The clearest category separation is in agentic, where the averages are 56.4 for Claude Opus 4.7 and 66.1 for Claude Sonnet 5.
- The biggest single benchmark swing is ApprenticeBench in Agentic, with scores of 7% and 16%.
- Claude Sonnet 5 is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.

## Model Snapshot

| Property | Claude Opus 4.7 | Claude Sonnet 5 |
|----------|----------|----------|
| Creator | Anthropic | Anthropic |
| Type | Proprietary | Proprietary |
| Reasoning | Non-Reasoning | Reasoning |
| Context | 1M | 1M |
| Overall Score | 70.94 | 69.62 |
| Benchmarks Covered | 14 | 26 |
| Pricing (input/output) | $5.00 / $25.00 | $2.00 / $10.00 |

## Category Breakdown

### Agentic

- Winner: Claude Sonnet 5
- Claude Opus 4.7 public-lane score: 56.4 (Supported · #36/154)
- Claude Sonnet 5 public-lane score: 66.1 (Supported · #11/154)

| Benchmark | Claude Opus 4.7 | Claude Sonnet 5 | Winner |
|-----------|-----------|-----------|--------|
| Gert Labs | 65.59% | Coming soon | Coming soon |
| ResearchClawBench | 20.7% | Coming soon | Coming soon |
| OSWorld 2.0 | 13.9% | Coming soon | Coming soon |
| Terminal-Bench 2.1 (Vals) | 68.5% | 74.5% | Claude Sonnet 5 |
| ApprenticeBench | 7% | 16% | Claude Sonnet 5 |
| Terminal-Bench 3.0 | Coming soon | 14.6% | Coming soon |
| Terminal-Bench 2.0 | Coming soon | 80.4% | Coming soon |
| BrowseComp | Coming soon | 84.7% | Coming soon |
| HLE w/ tools | Coming soon | 57.4% | Coming soon |
| OSWorld-Verified | Coming soon | 81.2% | Coming soon |

### Coding

- Winner: Claude Sonnet 5
- Claude Opus 4.7 public-lane score: 63.6 (Supported · #16/156)
- Claude Sonnet 5 public-lane score: 64.8 (Supported · #13/156)

| Benchmark | Claude Opus 4.7 | Claude Sonnet 5 | Winner |
|-----------|-----------|-----------|--------|
| Vibe Code Bench | 71.00% | Coming soon | Coming soon |
| React Native Evals | 82.8% | Coming soon | Coming soon |
| FrontierCode 1.1 Main | 38.5% | 42.7% | Claude Sonnet 5 |
| LiveCodeBench (Vals) | 85.1% | 82.4% | Claude Opus 4.7 |
| SWE-bench (Vals) | 82.0% | 79.6% | Claude Opus 4.7 |
| SWE-bench Verified | Coming soon | 85.2% | Coming soon |
| SWE-bench Pro | Coming soon | 63.2% | Coming soon |
| SWE Multilingual | Coming soon | 78.3% | Coming soon |
| SWE Multimodal | Coming soon | 28.1% | Coming soon |
| Terminal-Bench 2.0 | Coming soon | 80.4% | Coming soon |
| cursorBench32 | Coming soon | 61.5% | Coming soon |
| VulcanBench CII v1 | Coming soon | 89.2% | Coming soon |
| cursorBench40 | Coming soon | 34.1% | Coming soon |

### Reasoning

- Winner: Coming soon
- Claude Opus 4.7 public-lane score: Coming soon
- Claude Sonnet 5 public-lane score: 77.4 (Unranked · 2 rankable rows)

### Multimodal & Grounded

- Winner: Coming soon
- Claude Opus 4.7 public-lane score: Coming soon
- Claude Sonnet 5 public-lane score: 77.4 (#14/49)

| Benchmark | Claude Opus 4.7 | Claude Sonnet 5 | Winner |
|-----------|-----------|-----------|--------|
| CharXiv | Coming soon | 88.3% | Coming soon |
| CharXiv w/o tools | Coming soon | 77% | Coming soon |

### Knowledge

- Winner: Coming soon
- Claude Opus 4.7 public-lane score: 65.1 (Estimated · #25/186)
- Claude Sonnet 5 public-lane score: 66.8 (Supported · #20/186)

| Benchmark | Claude Opus 4.7 | Claude Sonnet 5 | Winner |
|-----------|-----------|-----------|--------|
| GPQA Diamond (Vals) | 90.2% | 88.9% | Claude Opus 4.7 |
| MMLU-Pro (Vals) | 89.9% | 87.5% | Claude Opus 4.7 |
| HLE | Coming soon | 57.4% | Coming soon |
| HLE w/o tools | Coming soon | 43.2% | Coming soon |
| HLE-Verified | Coming soon | 31.0% | Coming soon |
| LABBench2 | Coming soon | 80.1% | Coming soon |

### Mathematics

- Winner: Coming soon
- Claude Opus 4.7 public-lane score: 60.6 (Unranked · 2 rankable rows)
- Claude Sonnet 5 public-lane score: Coming soon

| Benchmark | Claude Opus 4.7 | Claude Sonnet 5 | Winner |
|-----------|-----------|-----------|--------|
| FrontierMath v2 (Tiers 1-3) | 43.793% | Coming soon | Coming soon |
| FrontierMath v2 (Tier 4) | 22.917% | Coming soon | Coming soon |

## FAQ

### Which is better overall, Claude Opus 4.7 or Claude Sonnet 5?

Claude Opus 4.7 is ahead overall on BenchLM right now.

### Where is the biggest gap between Claude Opus 4.7 and Claude Sonnet 5?

The widest category gap is in agentic, where the averages are 56.4 for Claude Opus 4.7 and 66.1 for Claude Sonnet 5.

### How many benchmarks does Claude Opus 4.7 cover on BenchLM?

Claude Opus 4.7 currently has 14 sourced benchmark scores on BenchLM.

### How many benchmarks does Claude Sonnet 5 cover on BenchLM?

Claude Sonnet 5 currently has 26 sourced benchmark scores on BenchLM.

## Related Comparisons

- [Claude Opus 4.7 vs Claude Opus 4.7 (Adaptive)](/compare/claude-opus-4-7-vs-claude-opus-4-7-adaptive)
- [Claude Sonnet 5 vs Claude Opus 4.7 (Adaptive)](/compare/claude-opus-4-7-adaptive-vs-claude-sonnet-5)
- [Claude Opus 4.7 vs Claude Fable 5.1](/compare/claude-fable-5-1-vs-claude-opus-4-7)
- [Claude Sonnet 5 vs Claude Fable 5.1](/compare/claude-fable-5-1-vs-claude-sonnet-5)

## Explore More

- [Claude Opus 4.7 profile](/models/claude-opus-4-7)
- [Claude Sonnet 5 profile](/models/claude-sonnet-5)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)