# GPT-4.1 mini vs GPT-5.2

> Side-by-side benchmark comparison for GPT-4.1 mini and GPT-5.2 across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/gpt-4-1-mini-vs-gpt-5-2
- Last updated: September 22, 2026

- Shared sourced benchmarks: 3
- HTML indexing: indexable
- Ranking lane: BenchAlign v5

## Quick Verdict

Evidence is too thin for a benchmark verdict: GPT-4.1 mini and GPT-5.2 share only 3 sourced benchmark rows.

## Summary

- Only 3 shared sourced benchmark rows are available. That is not enough for a broad capability verdict, so this mirror does not name an overall winner.
- GPT-4.1 mini has the lower published output-token price.
- GPT-4.1 mini has the larger published context window at 1M.

## Model Snapshot

| Property | GPT-4.1 mini | GPT-5.2 |
|----------|----------|----------|
| Creator | OpenAI | OpenAI |
| Type | Proprietary | Proprietary |
| Reasoning | Non-Reasoning | Reasoning |
| Context | 1M | 400K |
| Independent public score (not head-to-head) | 33.9 | 65.23 |
| Benchmarks Covered | 5 | 15 |
| Pricing (input/output) | $0.40 / $1.60 | $1.75 / $14.00 |

## Category Breakdown

### Agentic

- Winner: Insufficient shared evidence
- GPT-4.1 mini public-lane score: 37.7 (Estimated · #131/157)
- GPT-5.2 public-lane score: 48.2 (Supported · #75/157)

| Benchmark | GPT-4.1 mini | GPT-5.2 | Winner |
|-----------|-----------|-----------|--------|
| BrowseComp | Coming soon | 65.8% | Coming soon |
| OSWorld-Verified | Coming soon | 47.3% | Coming soon |
| Gert Labs | Coming soon | 46.54% | Coming soon |
| JobBench | Coming soon | 34.3% | Coming soon |

### Coding

- Winner: Insufficient shared evidence
- GPT-4.1 mini public-lane score: 36.1 (Estimated · #136/159)
- GPT-5.2 public-lane score: 46.2 (Supported · #87/159)

| Benchmark | GPT-4.1 mini | GPT-5.2 | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Verified | 23.6% | 80% | GPT-5.2 |
| SWE-bench Pro | Coming soon | 55.6% | Coming soon |
| Vibe Code Bench | Coming soon | 53.50% | Coming soon |

### Reasoning

- Winner: Insufficient shared evidence
- GPT-4.1 mini public-lane score: 51.3 (Unranked · 2 rankable rows)
- GPT-5.2 public-lane score: 53.7 (Unranked · 3 rankable rows)

| Benchmark | GPT-4.1 mini | GPT-5.2 | Winner |
|-----------|-----------|-----------|--------|
| ARC-AGI-2 | Coming soon | 52.9% | Coming soon |

### Multimodal & Grounded

- Winner: Insufficient shared evidence
- GPT-4.1 mini public-lane score: 46.6 (Unranked · 1 rankable row)
- GPT-5.2 public-lane score: 66.3 (#23/50)

| Benchmark | GPT-4.1 mini | GPT-5.2 | Winner |
|-----------|-----------|-----------|--------|
| MMMU-Pro | Coming soon | 79.5% | Coming soon |
| MathVision | Coming soon | 83.0% | Coming soon |
| CharXiv | Coming soon | 82.1% | Coming soon |
| V* | Coming soon | 75.9% | Coming soon |

### Knowledge

- Winner: Insufficient shared evidence
- GPT-4.1 mini public-lane score: 34.9 (Supported · #167/189)
- GPT-5.2 public-lane score: 61.8 (Supported · #32/189)

| Benchmark | GPT-4.1 mini | GPT-5.2 | Winner |
|-----------|-----------|-----------|--------|
| MMLU | 87.5% | Coming soon | Coming soon |
| GPQA | 64.2% | 92.4% | GPT-5.2 |

### Instruction Following

- Winner: Insufficient shared evidence
- GPT-4.1 mini public-lane score: 42.8 (#94/124)
- GPT-5.2 public-lane score: 91.2 (#15/124)

| Benchmark | GPT-4.1 mini | GPT-5.2 | Winner |
|-----------|-----------|-----------|--------|
| IFEval | 88.5% | Coming soon | Coming soon |

### Mathematics

- Winner: Insufficient shared evidence
- GPT-4.1 mini public-lane score: 28.4 (Unranked · 1 rankable row)
- GPT-5.2 public-lane score: 57.4 (Unranked · 2 rankable rows)

| Benchmark | GPT-4.1 mini | GPT-5.2 | Winner |
|-----------|-----------|-----------|--------|
| FrontierMath v2 (Tiers 1-3) | 4.483% | 40.700% | GPT-5.2 |
| FrontierMath v2 (Tier 4) | Coming soon | 18.800% | Coming soon |

## FAQ

### Is there enough evidence to pick between GPT-4.1 mini and GPT-5.2?

Not yet. The models share only 3 sourced benchmark rows, so this mirror reports the available measurements and metadata without naming a broad winner.

### What can I compare safely on this page?

Published pricing, context windows, model type, and individual shared benchmark rows are directly comparable. Independent overall scores and non-overlapping benchmark coverage are labeled separately and should not be read as a controlled head-to-head result.

## Related Comparisons

- [GPT-4.1 mini vs GPT-4.1](/compare/gpt-4-1-vs-gpt-4-1-mini)
- [GPT-5.2 vs GPT-4.1](/compare/gpt-4-1-vs-gpt-5-2)
- [GPT-4.1 mini vs GPT-4.1 nano](/compare/gpt-4-1-mini-vs-gpt-4-1-nano)
- [GPT-5.2 vs GPT-4.1 nano](/compare/gpt-4-1-nano-vs-gpt-5-2)

## Explore More

- [GPT-4.1 mini profile](/models/gpt-4-1-mini)
- [GPT-5.2 profile](/models/gpt-5-2)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)