# GPT-4.1 vs GPT-5 Pro

> GPT-5 Pro is the stronger model overall, scoring 46.2 to 35.7 on the Noometry Index. GPT-4.1 costs 12× less per token, which makes it the better buy when GPT-5 Pro's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gpt-4-1-vs-gpt-5-pro
- Last updated: 2026-10-10
- Shared benchmarks: 10

## Summary

- They share 10 benchmarks with published results for both. GPT-4.1 scores higher in 0 categories and GPT-5 Pro in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5 Pro leads 39.2 to 11.7.
- The biggest single-benchmark swing is ARC-AGI-1: 5.5% for GPT-4.1 and 70.2% for GPT-5 Pro.
- GPT-4.1 is cheaper at $2 / $8 per million input/output tokens, against $15 / $120 for GPT-5 Pro.
- GPT-4.1 accepts more context: 1.05M tokens versus 400K.

## Snapshot

| | GPT-4.1 | GPT-5 Pro |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 35.7 | 46.2 |
| Rank | 215 | 58 |
| Context | 1.05M | 400K |
| Input $/M | $2 | $15 |
| Output $/M | $8 | $120 |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-4.1: 34.2 (#228)
- GPT-5 Pro: 43.4 (#77)

| Benchmark | GPT-4.1 | GPT-5 Pro |
|---|---|---|
| WeirdML | 39% | 60.4% |
| SWE-bench Verified | 48.5% | — |
| SWE-bench Verified (bash only) | 39.6% | — |
| Aider Polyglot | 52.4% | — |
| LMArena Coding | 1391 | — |
| CadEval | 42% | — |
| ALE-Bench | 558.1 | — |
| AlgoTune | — | 1.31 |

## Agentic & Tool Use

- GPT-4.1: 34.4 (#40)
- GPT-5 Pro: —

| Benchmark | GPT-4.1 | GPT-5 Pro |
|---|---|---|
| Berkeley Function Calling Leaderboard | 54% | — |

## Reasoning

- GPT-4.1: 11.7 (#334)
- GPT-5 Pro: 39.2 (#52)

| Benchmark | GPT-4.1 | GPT-5 Pro |
|---|---|---|
| ARC-AGI-2 | 0.4% | 18.3% |
| SimpleBench | 27% | 61.6% |
| Kagi LLM Benchmark | 52.3% | 76.8% |
| ARC-AGI-1 | 5.5% | 70.2% |
| EnigmaEval | 2.2% | 18.8% |
| Epoch Capabilities Index | 136.79 | 150.26 |
| Chess Puzzles | 6% | — |
| LMArena Hard Prompts | 1384 | — |
| DTBench | 68.3% | — |
| LMCA | 25.6% | — |
| ForecastBench | 61.5 | — |

## Math

- GPT-4.1: 21.4 (#269)
- GPT-5 Pro: 48.0 (#53)

| Benchmark | GPT-4.1 | GPT-5 Pro |
|---|---|---|
| FrontierMath (Tiers 1-3) | 6% | 55.8% |
| FrontierMath Tier 4 (v1) | 0% | 14.6% |
| FrontierMath Tier 4 | — | 19.5% |
| OTIS Mock AIME 2024-2025 | 38.3% | — |
| Omni-MATH | 47.1% | — |
| LMArena Math | 1369 | — |
| MATH Level 5 | 83% | — |
| FrontierMath (Feb 2025 set) | 5.5% | — |

## Knowledge

- GPT-4.1: 37.0 (#152)
- GPT-5 Pro: 56.2 (#39)

| Benchmark | GPT-4.1 | GPT-5 Pro |
|---|---|---|
| Humanity's Last Exam | 5.4% | 31.6% |
| GPQA Diamond | 66.9% | — |
| SimpleQA Verified | 31.1% | — |
| MMLU-Pro | 81.1% | — |
| Vectara Hallucination Rate | 5.6% | — |
| GPQA (HELM) | 65.9% | — |
| LMArena Expert | 1364 | — |

## Multimodal

- GPT-4.1: 37.5 (#66)
- GPT-5 Pro: —

| Benchmark | GPT-4.1 | GPT-5 Pro |
|---|---|---|
| LMArena Vision | 1210 | — |
| GeoBench | 72% | — |

## Multilingual

- GPT-4.1: 49.6 (#128)
- GPT-5 Pro: —

| Benchmark | GPT-4.1 | GPT-5 Pro |
|---|---|---|
| LMArena Non-English | 1370 | — |
| LMArena Chinese | 1382 | — |
| LMArena French | 1383 | — |
| LMArena German | 1380 | — |
| LMArena Japanese | 1320 | — |
| LMArena Korean | 1339 | — |
| LMArena Russian | 1377 | — |
| LMArena Spanish | 1375 | — |

## Instruction Following

- GPT-4.1: 71.5 (#148)
- GPT-5 Pro: —

| Benchmark | GPT-4.1 | GPT-5 Pro |
|---|---|---|
| IFEval | 83.8% | — |
| LMArena Instruction Following | 1367 | — |

## Long Context

- GPT-4.1: 40.0 (#158)
- GPT-5 Pro: —

| Benchmark | GPT-4.1 | GPT-5 Pro |
|---|---|---|
| Fiction.LiveBench | 63.9% | — |
| LMArena Longer Query | 1385 | — |

## Writing & Preference

- GPT-4.1: 57.8 (#120)
- GPT-5 Pro: —

| Benchmark | GPT-4.1 | GPT-5 Pro |
|---|---|---|
| LMArena Text | 1383 | — |
| LMArena Creative Writing | 1363 | — |
| EQ-Bench Creative Writing | 1420 | — |
| WildBench | 85.4% | — |
| LMArena Multi-Turn | 1398 | — |

## FAQ

### Is GPT-4.1 better than GPT-5 Pro?

GPT-5 Pro is the stronger model overall, scoring 46.2 to 35.7 on the Noometry Index. GPT-4.1 costs 12× less per token, which makes it the better buy when GPT-5 Pro's lead doesn't matter for your workload.

### Which is cheaper, GPT-4.1 or GPT-5 Pro?

GPT-4.1 is cheaper. It lists at $2 per million input tokens and $8 per million output tokens; GPT-5 Pro lists at $15 and $120.

### Is GPT-4.1 or GPT-5 Pro better for coding?

GPT-5 Pro scores higher on coding benchmarks: 43.4 versus 34.2 in the Noometry coding category.

### Which has the bigger context window?

GPT-4.1 does, with 1.05M tokens against 400K.

### How many benchmarks do GPT-4.1 and GPT-5 Pro share?

10 benchmarks have published results for both models. GPT-4.1 has 52 scored results on Noometry and GPT-5 Pro has 12.