# Claude Sonnet 5 vs GPT-5.4

> Side-by-side benchmark comparison for Claude Sonnet 5 and GPT-5.4 across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/claude-sonnet-5-vs-gpt-5-4
- Last updated: September 22, 2026

- Shared sourced benchmarks: 7
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.6

## Quick Verdict

Pick GPT-5.4 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

- GPT-5.4 leads overall 69.23 to 67.25.
- The clearest category separation is in reasoning, where the averages are 77.4 for Claude Sonnet 5 and 57.2 for GPT-5.4.
- The biggest single benchmark swing is OSWorld-Verified in Agentic, with scores of 81.2% and 75%.
- Claude Sonnet 5 is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.
- GPT-5.4 also has the larger context window at 1.05M.

## Model Snapshot

| Property | Claude Sonnet 5 | GPT-5.4 |
|----------|----------|----------|
| Creator | Anthropic | OpenAI |
| Type | Proprietary | Proprietary |
| Reasoning | Reasoning | Reasoning |
| Context | 1M | 1.05M |
| Overall Score | 67.25 | 69.23 |
| Benchmarks Covered | 26 | 38 |
| Pricing (input/output) | $2.00 / $10.00 | $2.50 / $15.00 |

## Category Breakdown

### Agentic

- Winner: Claude Sonnet 5
- Claude Sonnet 5 public-lane score: 64.3 (Supported · #12/104)
- GPT-5.4 public-lane score: 50.1 (Supported · #34/104)

| Benchmark | Claude Sonnet 5 | GPT-5.4 | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 3.0 | 14.6% | Coming soon | Coming soon |
| Terminal-Bench 2.1 | 80.4% | Coming soon | Coming soon |
| BrowseComp | 84.7% | 82.7% | Claude Sonnet 5 |
| HLE w/ tools | 57.4% | Coming soon | Coming soon |
| OSWorld-Verified | 81.2% | 75% | Claude Sonnet 5 |
| Terminal-Bench 2.1 (Vals) | 74.5% | Coming soon | Coming soon |
| ApprenticeBench | 16% | 11% | Claude Sonnet 5 |
| Terminal-Bench 2.0 | Coming soon | 75.1% | Coming soon |
| CyberGym | Coming soon | 79.0% | Coming soon |
| MCP Atlas | Coming soon | 70.6% | Coming soon |
| Toolathlon | Coming soon | 54.6% | Coming soon |
| τ²-bench results | Coming soon | 98.9% | Coming soon |
| Claw-Eval | Coming soon | 60.3% | Coming soon |
| DeepSearchQA | Coming soon | 73.6% | Coming soon |
| Gert Labs | Coming soon | 64.89% | Coming soon |
| ResearchClawBench | Coming soon | 15.3% | Coming soon |
| JobBench | Coming soon | 38.9% | Coming soon |
| ExploitGym | Coming soon | 6.0% | Coming soon |

### Coding

- Winner: Claude Sonnet 5
- Claude Sonnet 5 public-lane score: 61.1 (Supported · #15/135)
- GPT-5.4 public-lane score: 50.9 (Supported · #38/135)

| Benchmark | Claude Sonnet 5 | GPT-5.4 | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Verified | 85.2% | Coming soon | Coming soon |
| SWE-bench Pro | 63.2% | 57.7% | Claude Sonnet 5 |
| SWE Multilingual | 78.3% | Coming soon | Coming soon |
| SWE Multimodal | 28.1% | Coming soon | Coming soon |
| Terminal-Bench 2.1 | 80.4% | Coming soon | Coming soon |
| FrontierCode 1.1 Main | 42.7% | Coming soon | Coming soon |
| cursorBench32 | 61.5% | Coming soon | Coming soon |
| VulcanBench CII v1 | 89.2% | Coming soon | Coming soon |
| LiveCodeBench (Vals) | 82.4% | Coming soon | Coming soon |
| SWE-bench (Vals) | 79.6% | Coming soon | Coming soon |
| cursorBench40 | 34.1% | Coming soon | Coming soon |
| LiveCodeBench Pro | Coming soon | 87.5% | Coming soon |
| React Native Evals | Coming soon | 85.3% | Coming soon |
| Vibe Code Bench | Coming soon | 67.42% | Coming soon |

### Reasoning

- Winner: Not comparable
- Claude Sonnet 5 public-lane score: 77.4 (Unranked · 2 rankable rows)
- GPT-5.4 public-lane score: 57.2 (#14/17)

| Benchmark | Claude Sonnet 5 | GPT-5.4 | Winner |
|-----------|-----------|-----------|--------|
| ARC-AGI-2 | Coming soon | 74.0% | Coming soon |
| ARC-AGI-3 | Coming soon | 0.2% | Coming soon |

### Multimodal & Grounded

- Winner: Directional only
- Claude Sonnet 5 public-lane score: 77.4 (#15/50)
- GPT-5.4 public-lane score: 69.3 (#21/50)

| Benchmark | Claude Sonnet 5 | GPT-5.4 | Winner |
|-----------|-----------|-----------|--------|
| CharXiv | 88.3% | 82.8% | Claude Sonnet 5 |
| CharXiv w/o tools | 77% | Coming soon | Coming soon |
| MMMU-Pro | Coming soon | 81.2% | Coming soon |
| OfficeQA Pro | Coming soon | 53.2% | Coming soon |
| MMMU-Pro w/ Python | Coming soon | 82.1% | Coming soon |
| ERQA | Coming soon | 65.4% | Coming soon |
| SimpleVQA | Coming soon | 61.1% | Coming soon |
| ScreenSpot Pro | Coming soon | 85.4% | Coming soon |
| ZeroBench | Coming soon | 41.0% | Coming soon |
| MedXpertQA (MM) | Coming soon | 77.1% | Coming soon |

### Knowledge

- Winner: GPT-5.4
- Claude Sonnet 5 public-lane score: 64.3 (Supported · #21/160)
- GPT-5.4 public-lane score: 66.5 (Supported · #17/160)

| Benchmark | Claude Sonnet 5 | GPT-5.4 | Winner |
|-----------|-----------|-----------|--------|
| HLE | 57.4% | 52.1% | Claude Sonnet 5 |
| HLE w/o tools | 43.2% | 39.8% | Claude Sonnet 5 |
| HLE-Verified | 31.0% | Coming soon | Coming soon |
| LABBench2 | 80.1% | Coming soon | Coming soon |
| GPQA Diamond (Vals) | 88.9% | Coming soon | Coming soon |
| MMLU-Pro (Vals) | 87.5% | Coming soon | Coming soon |
| GPQA | Coming soon | 92.8% | Coming soon |
| GPQA-D | Coming soon | 92.8% | Coming soon |
| HealthBench Hard | Coming soon | 40.1% | Coming soon |
| MedXpertQA (Text) | Coming soon | 59.6% | Coming soon |
| HealthBench Professional | Coming soon | 48.1% | Coming soon |

### Instruction Following

- Winner: Not comparable
- Claude Sonnet 5 public-lane score: Coming soon
- GPT-5.4 public-lane score: 89.2 (#19/124)

### Mathematics

- Winner: Not comparable
- Claude Sonnet 5 public-lane score: Coming soon
- GPT-5.4 public-lane score: 64.4 (Unranked · 2 rankable rows)

| Benchmark | Claude Sonnet 5 | GPT-5.4 | Winner |
|-----------|-----------|-----------|--------|
| FrontierMath v2 (Tiers 1-3) | Coming soon | 47.600% | Coming soon |
| FrontierMath v2 (Tier 4) | Coming soon | 27.100% | Coming soon |

## FAQ

### Which is better overall, Claude Sonnet 5 or GPT-5.4?

GPT-5.4 is ahead overall on BenchLM right now.

### Where is the biggest gap between Claude Sonnet 5 and GPT-5.4?

The widest category gap is in reasoning, where the averages are 77.4 for Claude Sonnet 5 and 57.2 for GPT-5.4.

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

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

### How many benchmarks does GPT-5.4 cover on BenchLM?

GPT-5.4 currently has 38 sourced benchmark scores on BenchLM.

## Related Comparisons

- [Claude Sonnet 5 vs GPT-5.4 Pro](/compare/claude-sonnet-5-vs-gpt-5-4-pro)
- [GPT-5.4 vs GPT-5.4 Pro](/compare/gpt-5-4-vs-gpt-5-4-pro)
- [Claude Sonnet 5 vs GPT-5.4 mini](/compare/claude-sonnet-5-vs-gpt-5-4-mini)
- [GPT-5.4 vs GPT-5.4 mini](/compare/gpt-5-4-vs-gpt-5-4-mini)

## Explore More

- [Claude Sonnet 5 profile](/models/claude-sonnet-5)
- [GPT-5.4 profile](/models/gpt-5-4)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)