# Claude Sonnet 5 vs GPT-5.4 mini

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

- Canonical page: https://benchlm.ai/compare/claude-sonnet-5-vs-gpt-5-4-mini
- Last updated: September 29, 2026

- Shared sourced benchmarks: 9
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.7

## Quick Verdict

Pick Claude Sonnet 5 if you want the stronger benchmark profile. GPT-5.4 mini 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 66.99 to 54.97.
- The clearest category separation is in reasoning, where the averages are 78.7 for Claude Sonnet 5 and 40 for GPT-5.4 mini.
- The biggest single benchmark swing is Terminal-Bench 2.1 (Vals) in Agentic, with scores of 74.5% and 54.7%.
- GPT-5.4 mini 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 5 | GPT-5.4 mini |
|----------|----------|----------|
| Creator | Anthropic | OpenAI |
| Type | Proprietary | Proprietary |
| Reasoning | Reasoning | Reasoning |
| Context | 1M | 400K |
| Overall Score | 66.99 | 54.97 |
| Benchmarks Covered | 26 | 21 |
| Pricing (input/output) | $2.00 / $10.00 | $0.75 / $4.50 |

## Category Breakdown

### Agentic

- Winner: Claude Sonnet 5
- Claude Sonnet 5 public-lane score: 64.6 (Supported · #12/117)
- GPT-5.4 mini public-lane score: 34 (Supported · #71/117)

| Benchmark | Claude Sonnet 5 | GPT-5.4 mini | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 3.0 | 14.6% | Coming soon | Coming soon |
| Terminal-Bench 2.1 | 80.4% | Coming soon | Coming soon |
| BrowseComp | 84.7% | Coming soon | Coming soon |
| HLE w/ tools | 57.4% | Coming soon | Coming soon |
| OSWorld-Verified | 81.2% | 72.1% | Claude Sonnet 5 |
| Terminal-Bench 2.1 (Vals) | 74.5% | 54.7% | Claude Sonnet 5 |
| ApprenticeBench | 16% | Coming soon | Coming soon |
| Terminal-Bench 2.0 | Coming soon | 60% | Coming soon |
| MCP Atlas | Coming soon | 57.7% | Coming soon |
| Toolathlon | Coming soon | 42.9% | Coming soon |
| τ²-bench results | Coming soon | 93.4% | Coming soon |

### Coding

- Winner: Claude Sonnet 5
- Claude Sonnet 5 public-lane score: 59.8 (Supported · #19/142)
- GPT-5.4 mini public-lane score: 36.9 (Supported · #71/142)

| Benchmark | Claude Sonnet 5 | GPT-5.4 mini | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Verified | 85.2% | Coming soon | Coming soon |
| SWE-bench Pro | 63.2% | Coming soon | Coming soon |
| 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% | 27.0% | Claude Sonnet 5 |
| cursorBench32 | 61.5% | Coming soon | Coming soon |
| VulcanBench CII v1 | 89.2% | Coming soon | Coming soon |
| LiveCodeBench (Vals) | 82.4% | 81.5% | Claude Sonnet 5 |
| SWE-bench (Vals) | 79.6% | 73.0% | Claude Sonnet 5 |
| cursorBench40 | 34.1% | Coming soon | Coming soon |
| Vibe Code Bench | Coming soon | 47.97% | Coming soon |

### Reasoning

- Winner: Not comparable
- Claude Sonnet 5 public-lane score: 78.7 (Unranked · 2 rankable rows)
- GPT-5.4 mini public-lane score: 40 (Unranked · 4 rankable rows)

| Benchmark | Claude Sonnet 5 | GPT-5.4 mini | Winner |
|-----------|-----------|-----------|--------|
| ARC-AGI-1 | Coming soon | 63.70% | Coming soon |
| ARC-AGI-2 | Coming soon | 18.9% | Coming soon |

### Multimodal & Grounded

- Winner: Directional only
- Claude Sonnet 5 public-lane score: 78.4 (#15/50)
- GPT-5.4 mini public-lane score: 58.3 (#33/50)

| Benchmark | Claude Sonnet 5 | GPT-5.4 mini | Winner |
|-----------|-----------|-----------|--------|
| CharXiv | 88.3% | Coming soon | Coming soon |
| CharXiv w/o tools | 77% | Coming soon | Coming soon |
| MMMU-Pro | Coming soon | 76.6% | Coming soon |
| MMMU-Pro w/ Python | Coming soon | 78% | Coming soon |

### Knowledge

- Winner: Claude Sonnet 5
- Claude Sonnet 5 public-lane score: 64.5 (Supported · #26/168)
- GPT-5.4 mini public-lane score: 48.4 (Supported · #65/168)

| Benchmark | Claude Sonnet 5 | GPT-5.4 mini | Winner |
|-----------|-----------|-----------|--------|
| HLE | 57.4% | 41.5% | Claude Sonnet 5 |
| HLE w/o tools | 43.2% | 28.2% | Claude Sonnet 5 |
| HLE-Verified | 31.0% | Coming soon | Coming soon |
| LABBench2 | 80.1% | Coming soon | Coming soon |
| GPQA Diamond (Vals) | 88.9% | 83.1% | Claude Sonnet 5 |
| MMLU-Pro (Vals) | 87.5% | 84.6% | Claude Sonnet 5 |
| GPQA | Coming soon | 88% | Coming soon |

### Instruction Following

- Winner: Not comparable
- Claude Sonnet 5 public-lane score: Coming soon
- GPT-5.4 mini public-lane score: 88.5 (#24/124)

### Mathematics

- Winner: Not comparable
- Claude Sonnet 5 public-lane score: Coming soon
- GPT-5.4 mini public-lane score: 44.3 (Unranked · 2 rankable rows)

| Benchmark | Claude Sonnet 5 | GPT-5.4 mini | Winner |
|-----------|-----------|-----------|--------|
| FrontierMath v2 (Tiers 1-3) | Coming soon | 28.280% | Coming soon |
| FrontierMath v2 (Tier 4) | Coming soon | 2.080% | Coming soon |

## FAQ

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

Claude Sonnet 5 is ahead overall on BenchLM right now.

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

The widest category gap is in reasoning, where the averages are 78.7 for Claude Sonnet 5 and 40 for GPT-5.4 mini.

### 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 mini cover on BenchLM?

GPT-5.4 mini currently has 21 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 mini vs GPT-5.4 Pro](/compare/gpt-5-4-mini-vs-gpt-5-4-pro)
- [Claude Sonnet 5 vs GPT-5.4](/compare/claude-sonnet-5-vs-gpt-5-4)
- [GPT-5.4 mini vs GPT-5.4](/compare/gpt-5-4-vs-gpt-5-4-mini)

## Explore More

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