# GPT-4.1 mini vs GPT-5.1

> GPT-5.1 is the stronger model overall, scoring 49.0 to 33.6 on the Noometry Index. GPT-4.1 mini costs 4.9× less per token, which makes it the better buy when GPT-5.1's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gpt-4-1-mini-vs-gpt-5-1
- Last updated: 2026-10-12
- Shared benchmarks: 38

## Summary

- They share 38 benchmarks with published results for both. GPT-4.1 mini scores higher in 1 category and GPT-5.1 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5.1 leads 39.8 to 10.8.
- The biggest single-benchmark swing is ARC-AGI-1: 3.5% for GPT-4.1 mini and 72.8% for GPT-5.1.
- GPT-4.1 mini is cheaper at $0.40 / $1.60 per million input/output tokens, against $1.25 / $10 for GPT-5.1.
- GPT-4.1 mini accepts more context: 1.05M tokens versus 400K.

## Snapshot

| | GPT-4.1 mini | GPT-5.1 |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 33.6 | 49.0 |
| Rank | 240 | 53 |
| Context | 1.05M | 400K |
| Input $/M | $0.40 | $1.25 |
| Output $/M | $1.60 | $10 |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-4.1 mini: 30.6 (#293)
- GPT-5.1: 46.4 (#66)

| Benchmark | GPT-4.1 mini | GPT-5.1 |
|---|---|---|
| SWE-bench Verified (bash only) | 23.9% | 66% |
| SciCode | 40.4% | 43.3% |
| WeirdML | 37.6% | 60.8% |
| LMArena Coding | 1367 | 1454 |
| SWE-bench Verified | — | 68% |
| Aider Polyglot | 32.4% | — |
| LMArena WebDev | — | 1395 |
| GSO | — | 13.7% |
| BigCodeBench Instruct | 48.9% | — |
| LiveBench Coding | — | 72.5% |
| CadEval | 16% | — |
| ALE-Bench | — | 1,192 |

## Agentic & Tool Use

- GPT-4.1 mini: 33.3 (#55)
- GPT-5.1: 32.7 (#60)

| Benchmark | GPT-4.1 mini | GPT-5.1 |
|---|---|---|
| Terminal-Bench | — | 47.6% |
| Berkeley Function Calling Leaderboard | 50.5% | — |
| DeepResearch Bench | — | 42.8% |
| LMArena Search | — | 1199 |
| Vending-Bench 2 | — | 1,473 |

## Reasoning

- GPT-4.1 mini: 10.8 (#340)
- GPT-5.1: 39.8 (#58)

| Benchmark | GPT-4.1 mini | GPT-5.1 |
|---|---|---|
| ARC-AGI-2 | 0% | 17.6% |
| ARC-AGI-1 | 3.5% | 72.8% |
| CritPt | 0% | 4.9% |
| Chess Puzzles | 7% | 32% |
| LMArena Hard Prompts | 1349 | 1457 |
| Mystery Game Puzzles | 7% | 19% |
| DTBench | 68.8% | 90.1% |
| LMCA | 21.1% | 43.9% |
| Epoch Capabilities Index | 135.01 | 149.64 |
| SimpleBench | — | 53.2% |
| Kagi LLM Benchmark | 48.6% | — |
| EnigmaEval | — | 11.2% |
| LiveBench Reasoning | — | 95.8% |
| LiveBench Data Analysis | — | 72.1% |
| ForecastBench | — | 58.1 |
| LiveBench | — | 78.8% |

## Math

- GPT-4.1 mini: 24.1 (#270)
- GPT-5.1: 52.2 (#51)

| Benchmark | GPT-4.1 mini | GPT-5.1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 44.7% | 88.6% |
| Omni-MATH | 49.1% | 46.4% |
| LMArena Math | 1343 | 1447 |
| FrontierMath (Feb 2025 set) | 4.5% | 31% |
| FrontierMath (Tiers 1-3) | 6.7% | — |
| LiveBench Math | — | 94.5% |
| MATH Level 5 | 87.3% | — |
| FrontierMath Tier 4 (v1) | — | 12.5% |

## Knowledge

- GPT-4.1 mini: 34.7 (#194)
- GPT-5.1: 50.6 (#71)

| Benchmark | GPT-4.1 mini | GPT-5.1 |
|---|---|---|
| GPQA Diamond | 65.8% | 87.6% |
| SimpleQA Verified | 12.7% | 48% |
| MMLU-Pro | 78.3% | 57.9% |
| GPQA (HELM) | 61.4% | 44.2% |
| LMArena Expert | 1338 | 1470 |
| Humanity's Last Exam | — | 23.7% |
| Vectara Hallucination Rate | — | 10.9% |

## Multimodal

- GPT-4.1 mini: 35.8 (#82)
- GPT-5.1: 44.8 (#19)

| Benchmark | GPT-4.1 mini | GPT-5.1 |
|---|---|---|
| LMArena Vision | 1181 | 1250 |
| VPCT | — | 58.7% |
| LMArena Document | — | 1403 |

## Multilingual

- GPT-4.1 mini: 45.7 (#166)
- GPT-5.1: 53.8 (#56)

| Benchmark | GPT-4.1 mini | GPT-5.1 |
|---|---|---|
| LMArena Non-English | 1318 | 1431 |
| LMArena Chinese | 1329 | 1495 |
| LMArena French | 1358 | 1450 |
| LMArena German | 1351 | 1438 |
| LMArena Japanese | 1290 | 1453 |
| LMArena Korean | 1298 | 1401 |
| LMArena Russian | 1324 | 1435 |
| LMArena Spanish | 1319 | 1433 |

## Instruction Following

- GPT-4.1 mini: 73.7 (#118)
- GPT-5.1: 83.9 (#1)

| Benchmark | GPT-4.1 mini | GPT-5.1 |
|---|---|---|
| IFEval | 90.4% | 93.5% |
| LMArena Instruction Following | 1333 | 1443 |
| LiveBench Instruction Following | — | 93.3% |

## Long Context

- GPT-4.1 mini: 31.8 (#275)
- GPT-5.1: 47.6 (#14)

| Benchmark | GPT-4.1 mini | GPT-5.1 |
|---|---|---|
| LMArena Longer Query | 1344 | 1447 |
| Fiction.LiveBench | 44.4% | — |
| CL-bench | — | 23.7% |
| CL-bench Life | — | 17.3% |

## Writing & Preference

- GPT-4.1 mini: 48.6 (#199)
- GPT-5.1: 64.5 (#55)

| Benchmark | GPT-4.1 mini | GPT-5.1 |
|---|---|---|
| LMArena Text | 1340 | 1443 |
| LMArena Creative Writing | 1300 | 1427 |
| WildBench | 83.8% | 86.3% |
| LMArena Multi-Turn | 1354 | 1450 |
| EQ-Bench Creative Writing | 1147 | — |
| LiveBench Language | — | 80.2% |

## FAQ

### Is GPT-4.1 mini better than GPT-5.1?

GPT-5.1 is the stronger model overall, scoring 49.0 to 33.6 on the Noometry Index. GPT-4.1 mini costs 4.9× less per token, which makes it the better buy when GPT-5.1's lead doesn't matter for your workload.

### Which is cheaper, GPT-4.1 mini or GPT-5.1?

GPT-4.1 mini is cheaper. It lists at $0.40 per million input tokens and $1.60 per million output tokens; GPT-5.1 lists at $1.25 and $10.

### Is GPT-4.1 mini or GPT-5.1 better for coding?

GPT-5.1 scores higher on coding benchmarks: 46.4 versus 30.6 in the Noometry coding category.

### Which has the bigger context window?

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

### How many benchmarks do GPT-4.1 mini and GPT-5.1 share?

38 benchmarks have published results for both models. GPT-4.1 mini has 47 scored results on Noometry and GPT-5.1 has 63.