# GPT-5.2 Pro vs GPT-5 Mini

> GPT-5.2 Pro is the stronger model overall, scoring 52.3 to 41.8 on the Noometry Index. GPT-5 Mini costs 84× less per token, which makes it the better buy when GPT-5.2 Pro's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gpt-5-2-pro-vs-gpt-5-mini
- Last updated: 2026-10-12
- Shared benchmarks: 6

## Summary

- They share 6 benchmarks with published results for both. GPT-5.2 Pro scores higher in 2 categories and GPT-5 Mini in 0 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5.2 Pro leads 51.5 to 23.9.
- The biggest single-benchmark swing is ARC-AGI-2: 54.2% for GPT-5.2 Pro and 4.4% for GPT-5 Mini.
- GPT-5 Mini is cheaper at $0.25 / $2 per million input/output tokens, against $21 / $168 for GPT-5.2 Pro.

## Snapshot

| | GPT-5.2 Pro | GPT-5 Mini |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 52.3 | 41.8 |
| Rank | 39 | 128 |
| Context | 400K | 400K |
| Input $/M | $21 | $0.25 |
| Output $/M | $168 | $2 |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-5.2 Pro: —
- GPT-5 Mini: 40.1 (#146)

| Benchmark | GPT-5.2 Pro | GPT-5 Mini |
|---|---|---|
| SWE-bench Verified | — | 64.7% |
| SWE-bench Verified (bash only) | — | 59.8% |
| SWE-bench Multilingual | — | 39.7% |
| SciCode | — | 39.2% |
| WeirdML | — | 52.7% |
| LMArena Coding | — | 1406 |
| ALE-Bench | — | 799.77 |
| AlgoTune | — | 1.38 |

## Agentic & Tool Use

- GPT-5.2 Pro: —
- GPT-5 Mini: 31.1 (#70)

| Benchmark | GPT-5.2 Pro | GPT-5 Mini |
|---|---|---|
| Terminal-Bench | — | 34.8% |
| Berkeley Function Calling Leaderboard | — | 55.5% |
| Vending-Bench 2 | — | -31.18 |

## Reasoning

- GPT-5.2 Pro: 51.5 (#33)
- GPT-5 Mini: 23.9 (#168)

| Benchmark | GPT-5.2 Pro | GPT-5 Mini |
|---|---|---|
| ARC-AGI-2 | 54.2% | 4.4% |
| ARC-AGI-1 | 90.5% | 54.3% |
| Epoch Capabilities Index | 155.4 | 145.52 |
| SimpleBench | 57.4% | — |
| Kagi LLM Benchmark | — | 70.3% |
| NYT Connections (extended) | 79.3% | — |
| CritPt | — | 0% |
| Chess Puzzles | — | 30% |
| EnigmaEval | — | 8.2% |
| LMArena Hard Prompts | — | 1380 |
| Mystery Game Puzzles | — | 10% |
| DTBench | — | 80.5% |
| LMCA | — | 34.2% |
| ForecastBench | — | 61 |

## Math

- GPT-5.2 Pro: 65.3 (#29)
- GPT-5 Mini: 46.7 (#69)

| Benchmark | GPT-5.2 Pro | GPT-5 Mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 74% | 46.7% |
| FrontierMath Tier 4 | 46% | 12.2% |
| FrontierMath Tier 4 (v1) | 31.3% | 6.3% |
| OTIS Mock AIME 2024-2025 | — | 86.7% |
| ProofBench | — | 9% |
| Omni-MATH | — | 72.2% |
| LMArena Math | — | 1378 |
| MATH Level 5 | — | 97.8% |
| FrontierMath (Feb 2025 set) | — | 27.2% |

## Knowledge

- GPT-5.2 Pro: —
- GPT-5 Mini: 45.6 (#86)

| Benchmark | GPT-5.2 Pro | GPT-5 Mini |
|---|---|---|
| GPQA Diamond | — | 75% |
| Humanity's Last Exam | — | 19.4% |
| SimpleQA Verified | — | 21.6% |
| MMLU-Pro | — | 83.5% |
| Confabulations | — | 13.3% |
| Vectara Hallucination Rate | — | 12.9% |
| GPQA (HELM) | — | 75.6% |
| LMArena Expert | — | 1379 |

## Multimodal

- GPT-5.2 Pro: —
- GPT-5 Mini: 35.6 (#85)

| Benchmark | GPT-5.2 Pro | GPT-5 Mini |
|---|---|---|
| LMArena Vision | — | 1202 |
| VPCT | — | 40.2% |

## Multilingual

- GPT-5.2 Pro: —
- GPT-5 Mini: 48.9 (#137)

| Benchmark | GPT-5.2 Pro | GPT-5 Mini |
|---|---|---|
| LMArena Non-English | — | 1363 |
| LMArena Chinese | — | 1385 |
| LMArena French | — | 1386 |
| LMArena German | — | 1366 |
| LMArena Japanese | — | 1341 |
| LMArena Korean | — | 1308 |
| LMArena Russian | — | 1362 |
| LMArena Spanish | — | 1355 |

## Instruction Following

- GPT-5.2 Pro: —
- GPT-5 Mini: 76.2 (#46)

| Benchmark | GPT-5.2 Pro | GPT-5 Mini |
|---|---|---|
| IFEval | — | 92.7% |
| LMArena Instruction Following | — | 1357 |

## Long Context

- GPT-5.2 Pro: —
- GPT-5 Mini: 41.9 (#132)

| Benchmark | GPT-5.2 Pro | GPT-5 Mini |
|---|---|---|
| Fiction.LiveBench | — | 69.4% |
| LMArena Longer Query | — | 1355 |

## Writing & Preference

- GPT-5.2 Pro: —
- GPT-5 Mini: 55.2 (#148)

| Benchmark | GPT-5.2 Pro | GPT-5 Mini |
|---|---|---|
| LMArena Text | — | 1373 |
| LMArena Creative Writing | — | 1325 |
| Short-Story Creative Writing | — | 83.1% |
| EQ-Bench Creative Writing | — | 1313 |
| WildBench | — | 85.5% |
| LMArena Multi-Turn | — | 1363 |

## FAQ

### Is GPT-5.2 Pro better than GPT-5 Mini?

GPT-5.2 Pro is the stronger model overall, scoring 52.3 to 41.8 on the Noometry Index. GPT-5 Mini costs 84× less per token, which makes it the better buy when GPT-5.2 Pro's lead doesn't matter for your workload.

### Which is cheaper, GPT-5.2 Pro or GPT-5 Mini?

GPT-5 Mini is cheaper. It lists at $0.25 per million input tokens and $2 per million output tokens; GPT-5.2 Pro lists at $21 and $168.

### Which has the bigger context window?

Both accept 400K tokens.

### How many benchmarks do GPT-5.2 Pro and GPT-5 Mini share?

6 benchmarks have published results for both models. GPT-5.2 Pro has 8 scored results on Noometry and GPT-5 Mini has 60.