# GPT-5 vs GPT-5.4 mini

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

- Canonical page: https://benchlm.ai/compare/gpt-5-vs-gpt-5-4-mini
- Last updated: November 18, 2026

- Shared sourced benchmarks: 5
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

GPT-5.4 mini leads by point estimate. Conditional score ranges do not establish rank confidence. Choose using the category evidence and your own workload tests.

## Summary

- GPT-5.4 mini has the higher overall point estimate 52.06 to 48.96. Conditional score ranges do not establish rank confidence.
- The clearest category separation is in reasoning, where the averages are 43.7 for GPT-5 and 30.5 for GPT-5.4 mini.
- The biggest single benchmark swing is Vibe Code Bench in Coding, with scores of 20.09% and 47.97%.
- GPT-5.4 mini is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.
- GPT-5.4 mini also has the larger context window at 400K.

## Model Snapshot

| Property | GPT-5 | GPT-5.4 mini |
|----------|----------|----------|
| Creator | OpenAI | OpenAI |
| Type | Proprietary | Proprietary |
| Reasoning | Reasoning | Reasoning |
| Context | 128K | 400K |
| Overall Score | 48.96 | 52.06 |
| Benchmarks Covered | 6 | 23 |
| Pricing (input/output) | $1.25 / $10.00 | $0.75 / $4.50 |

## Category Breakdown

### Agentic

- Winner: Not comparable
- GPT-5 public-lane score: Coming soon
- GPT-5.4 mini public-lane score: 37.4 (Supported · #84/138)

| Benchmark | GPT-5 | GPT-5.4 mini | Winner |
|-----------|-----------|-----------|--------|
| JobBench | 8.5% | Coming soon | Coming soon |
| Terminal-Bench 4.1 | Coming soon | 1.80% | Coming soon |
| Terminal-Bench 2.0 | Coming soon | 60% | Coming soon |
| OSWorld-Verified | Coming soon | 72.1% | 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 |
| Terminal-Bench 2.1 (Vals) | Coming soon | 54.7% | Coming soon |

### Coding

- Winner: Directional only
- GPT-5 public-lane score: 36.7 (Estimated · #85/160)
- GPT-5.4 mini public-lane score: 33.9 (Supported · #91/160)

| Benchmark | GPT-5 | GPT-5.4 mini | Winner |
|-----------|-----------|-----------|--------|
| Vibe Code Bench | 20.09% | 47.97% | GPT-5.4 mini |
| LiveCodeBench (Vals) | 85.9% | 81.5% | GPT-5 |
| SWE-bench (Vals) | 69.0% | 73.0% | GPT-5.4 mini |
| Terminal-Bench 2.0 | Coming soon | 60.0% | Coming soon |
| FrontierCode 1.1 Main | Coming soon | 27.0% | Coming soon |

### Reasoning

- Winner: Directional only
- GPT-5 public-lane score: 43.7 (Estimated · #75/159)
- GPT-5.4 mini public-lane score: 30.5 (Supported · #113/159)

| Benchmark | GPT-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: Not comparable
- GPT-5 public-lane score: Coming soon
- GPT-5.4 mini public-lane score: Coming soon

| Benchmark | GPT-5 | GPT-5.4 mini | Winner |
|-----------|-----------|-----------|--------|
| MMMU-Pro | Coming soon | 76.6% | Coming soon |
| MMMU-Pro w/ Python | Coming soon | 78% | Coming soon |

### Knowledge

- Winner: GPT-5
- GPT-5 public-lane score: 53.1 (Supported · #67/179)
- GPT-5.4 mini public-lane score: 51.4 (Supported · #74/179)

| Benchmark | GPT-5 | GPT-5.4 mini | Winner |
|-----------|-----------|-----------|--------|
| GPQA Diamond (Vals) | 85.6% | 83.1% | GPT-5 |
| MMLU-Pro (Vals) | 86.5% | 84.6% | GPT-5 |
| GPQA | Coming soon | 88% | Coming soon |
| HLE | Coming soon | 41.5% | Coming soon |
| HLE w/o tools | Coming soon | 28.2% | Coming soon |

### Instruction Following

- Winner: Directional only
- GPT-5 public-lane score: 89.4 (#35/157)
- GPT-5.4 mini public-lane score: 89.6 (#33/157)

### Mathematics

- Winner: Not comparable
- GPT-5 public-lane score: Coming soon
- GPT-5.4 mini public-lane score: 51 (Unranked · 2 rankable rows)

| Benchmark | GPT-5 | GPT-5.4 mini | Winner |
|-----------|-----------|-----------|--------|
| FrontierMath v2 (Tiers 1-3) | Coming soon | 51.228% | Coming soon |
| FrontierMath v2 (Tier 4) | Coming soon | 9.756% | Coming soon |

## FAQ

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

GPT-5.4 mini has the higher overall point estimate. Conditional score ranges do not establish rank confidence.

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

The widest category gap is in reasoning, where the averages are 43.7 for GPT-5 and 30.5 for GPT-5.4 mini.

### How many benchmarks does GPT-5 cover on BenchLM?

GPT-5 currently has 6 sourced benchmark scores on BenchLM.

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

GPT-5.4 mini currently has 23 sourced benchmark scores on BenchLM.

## Related Comparisons

- [GPT-5 vs GPT-5 mini](/compare/gpt-5-vs-gpt-5-mini)
- [GPT-5.4 mini vs GPT-5 mini](/compare/gpt-5-4-mini-vs-gpt-5-mini)
- [GPT-5 vs GPT-5 nano](/compare/gpt-5-vs-gpt-5-nano)
- [GPT-5.4 mini vs GPT-5 nano](/compare/gpt-5-4-mini-vs-gpt-5-nano)

## Explore More

- [GPT-5 profile](/models/gpt-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)
