# Claude Sonnet 4.6 vs Claude Sonnet 5

> Side-by-side benchmark comparison for Claude Sonnet 4.6 and Claude Sonnet 5 across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/claude-sonnet-4-6-vs-claude-sonnet-5
- Last updated: September 18, 2026

- Shared sourced benchmarks: 12
- HTML indexing: indexable
- Ranking lane: BenchAlign v5

## Quick Verdict

Pick Claude Sonnet 5 if you want the stronger benchmark profile. Claude Sonnet 4.6 only makes more sense when its price, context window, or workload-specific category wins matter more than the overall score.

## Summary

- Claude Sonnet 5 leads overall 69.68 to 62.86.
- The clearest category separation is in multimodal & grounded, where the averages are 54.1 for Claude Sonnet 4.6 and 77.4 for Claude Sonnet 5.
- The biggest single benchmark swing is Terminal-Bench 2.0 in Agentic, with scores of 59.1% and 80.4%.
- Claude Sonnet 5 is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.
- Claude Sonnet 5 also has the larger context window at 1M.

## Model Snapshot

| Property | Claude Sonnet 4.6 | Claude Sonnet 5 |
|----------|----------|----------|
| Creator | Anthropic | Anthropic |
| Type | Proprietary | Proprietary |
| Reasoning | Non-Reasoning | Reasoning |
| Context | 200K | 1M |
| Overall Score | 62.86 | 69.68 |
| Benchmarks Covered | 26 | 26 |
| Pricing (input/output) | $3.00 / $15.00 | $2.00 / $10.00 |

## Category Breakdown

### Agentic

- Winner: Claude Sonnet 5
- Claude Sonnet 4.6 public-lane score: 43.8 (Supported · #95/154)
- Claude Sonnet 5 public-lane score: 65.9 (Supported · #11/154)

| Benchmark | Claude Sonnet 4.6 | Claude Sonnet 5 | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.0 | 59.1% | 80.4% | Claude Sonnet 5 |
| OSWorld-Verified | 72.1% | 81.2% | Claude Sonnet 5 |
| Claw-Eval | 67.8% | Coming soon | Coming soon |
| CyberGym | 65.2% | Coming soon | Coming soon |
| Gert Labs | 62.92% | Coming soon | Coming soon |
| OSWorld 2.0 | 8.3% | Coming soon | Coming soon |
| JobBench | 36.9% | Coming soon | Coming soon |
| Terminal-Bench 2.1 (Vals) | 57.3% | 74.5% | Claude Sonnet 5 |
| ApprenticeBench | 2% | 16% | Claude Sonnet 5 |
| Terminal-Bench 3.0 | Coming soon | 14.6% | Coming soon |
| BrowseComp | Coming soon | 84.7% | Coming soon |
| HLE w/ tools | Coming soon | 57.4% | Coming soon |

### Coding

- Winner: Claude Sonnet 5
- Claude Sonnet 4.6 public-lane score: 52.2 (Supported · #49/154)
- Claude Sonnet 5 public-lane score: 63.9 (Supported · #13/154)

| Benchmark | Claude Sonnet 4.6 | Claude Sonnet 5 | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Verified | 79.6% | 85.2% | Claude Sonnet 5 |
| SWE-Rebench | 60.7% | Coming soon | Coming soon |
| React Native Evals | 80.6% | Coming soon | Coming soon |
| Vibe Code Bench | 51.48% | Coming soon | Coming soon |
| cursorBench31 | 48.8% | Coming soon | Coming soon |
| FrontierCode 1.1 Main | 24.3% | 42.7% | Claude Sonnet 5 |
| LiveCodeBench (Vals) | 82.1% | 82.4% | Claude Sonnet 5 |
| SWE-bench (Vals) | 77.4% | 79.6% | Claude Sonnet 5 |
| 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 |

### Multimodal & Grounded

- Winner: Claude Sonnet 5
- Claude Sonnet 4.6 public-lane score: 54.1 (#33/48)
- Claude Sonnet 5 public-lane score: 77.4 (#14/48)

| Benchmark | Claude Sonnet 4.6 | Claude Sonnet 5 | Winner |
|-----------|-----------|-----------|--------|
| CharXiv | 77.4% | 88.3% | Claude Sonnet 5 |
| CharXiv w/o tools | Coming soon | 77% | Coming soon |

### Reasoning

- Winner: Coming soon
- Claude Sonnet 4.6 public-lane score: 67.9 (Unranked · 2 rankable rows)
- Claude Sonnet 5 public-lane score: 77.4 (Unranked · 2 rankable rows)

### Knowledge

- Winner: Claude Sonnet 5
- Claude Sonnet 4.6 public-lane score: 55.7 (Supported · #51/184)
- Claude Sonnet 5 public-lane score: 66.5 (Supported · #20/184)

| Benchmark | Claude Sonnet 4.6 | Claude Sonnet 5 | Winner |
|-----------|-----------|-----------|--------|
| GPQA | 89.9% | Coming soon | Coming soon |
| SuperGPQA | 95% | Coming soon | Coming soon |
| MMLU-Pro | 79.2% | Coming soon | Coming soon |
| HLE | 49% | 57.4% | Claude Sonnet 5 |
| GPQA Diamond (Vals) | 85.6% | 88.9% | Claude Sonnet 5 |
| MMLU-Pro (Vals) | 87.3% | 87.5% | Claude Sonnet 5 |
| 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 |

### Instruction Following

- Winner: Coming soon
- Claude Sonnet 4.6 public-lane score: 46.6 (#88/124)
- Claude Sonnet 5 public-lane score: Coming soon

### Mathematics

- Winner: Coming soon
- Claude Sonnet 4.6 public-lane score: 48.8 (Unranked · 2 rankable rows)
- Claude Sonnet 5 public-lane score: Coming soon

| Benchmark | Claude Sonnet 4.6 | Claude Sonnet 5 | Winner |
|-----------|-----------|-----------|--------|
| FrontierMath v2 (Tiers 1-3) | 32.400% | Coming soon | Coming soon |
| FrontierMath v2 (Tier 4) | 8.300% | Coming soon | Coming soon |

## FAQ

### Which is better overall, Claude Sonnet 4.6 or Claude Sonnet 5?

Claude Sonnet 5 is ahead overall on BenchLM right now.

### Where is the biggest gap between Claude Sonnet 4.6 and Claude Sonnet 5?

The widest category gap is in multimodal & grounded, where the averages are 54.1 for Claude Sonnet 4.6 and 77.4 for Claude Sonnet 5.

### How many benchmarks does Claude Sonnet 4.6 cover on BenchLM?

Claude Sonnet 4.6 currently has 26 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 Sonnet 4.6 vs Claude Fable 5.1](/compare/claude-fable-5-1-vs-claude-sonnet-4-6)
- [Claude Sonnet 5 vs Claude Fable 5.1](/compare/claude-fable-5-1-vs-claude-sonnet-5)
- [Claude Sonnet 4.6 vs GPT-6 Astra](/compare/claude-sonnet-4-6-vs-gpt-6-astra)
- [Claude Sonnet 5 vs GPT-6 Astra](/compare/claude-sonnet-5-vs-gpt-6-astra)

## Explore More

- [Claude Sonnet 4.6 profile](/models/claude-sonnet-4-6)
- [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)