Model comparison
GPT-4.1 mini vs GPT-5.2
GPT-5.2 is the stronger model overall, scoring 54.1 to 33.5 on the Noometry Index. GPT-4.1 mini costs 6.9× less per token, which makes it the better buy when GPT-5.2's lead doesn't matter for your workload.
Last verified . 35 shared benchmarks.
Summary
- They share 35 benchmarks with published results for both. GPT-4.1 mini scores higher in 0 categories and GPT-5.2 in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5.2 leads 50.1 to 10.9.
- The biggest single-benchmark swing is ARC-AGI-1: 3.5% for GPT-4.1 mini and 86.2% for GPT-5.2.
- GPT-4.1 mini is cheaper at $0.40 / $1.60 per million input/output tokens, against $1.75 / $14 for GPT-5.2.
- GPT-4.1 mini accepts more context: 1.05M tokens versus 400K.
Side by side
| GPT-4.1 mini | GPT-5.2 | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 33.5 | 54.1 |
| Released | 2025-04-14 | 2025-12-11 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 400K |
| Max output | 33K | 128K |
| Input $ / M tokens | $0.40 | $1.75 |
| Output $ / M tokens | $1.60 | $14 |
| Results tracked | 47 | 67 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.2 leads
GPT-4.1 mini: 30.4 (#286), GPT-5.2: 52.2 (#32)
| Benchmark | GPT-4.1 mini | GPT-5.2 |
|---|---|---|
| SWE-bench Verified (bash only) | 23.9% | 72.8% |
| WeirdML | 37.6% | 72.2% |
| LMArena Coding | 1367 | 1447 |
| SWE-bench Verified | — | 73.8% |
| Aider Polyglot | 32.4% | — |
| LMArena WebDev | — | 1415 |
| SWE-bench Multilingual | — | 66.7% |
| SciCode | 40.4% | — |
| GSO | — | 27.4% |
| BigCodeBench Instruct | 48.9% | — |
| CadEval | 16% | — |
| ALE-Bench | — | 1,294 |
| AlgoTune | — | 2.05 |
Agentic & Tool Use GPT-5.2 leads
GPT-4.1 mini: 33.0 (#52), GPT-5.2: 40.0 (#24)
| Benchmark | GPT-4.1 mini | GPT-5.2 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 50.5% | 55.9% |
| Terminal-Bench | — | 64.9% |
| GDPval | — | 49.7% |
| Remote Labor Index | — | 2.5% |
| τ²-bench Airline | — | 83% |
| τ²-bench Banking | — | 32.2% |
| τ²-bench Retail | — | 81.6% |
| τ²-bench Telecom | — | 89.7% |
| DeepResearch Bench | — | 41.1% |
| LMArena Search | — | 1207 |
| METR Time Horizons | — | 75.3% |
| Vending-Bench 2 | — | 3,591 |
Reasoning GPT-5.2 leads
GPT-4.1 mini: 10.9 (#335), GPT-5.2: 50.1 (#33)
| Benchmark | GPT-4.1 mini | GPT-5.2 |
|---|---|---|
| ARC-AGI-2 | 0% | 52.9% |
| Kagi LLM Benchmark | 48.6% | 73.3% |
| ARC-AGI-1 | 3.5% | 86.2% |
| Chess Puzzles | 7% | 49% |
| LMArena Hard Prompts | 1349 | 1445 |
| Mystery Game Puzzles | 7% | 23% |
| DTBench | 68.8% | 90.9% |
| LMCA | 21.1% | 43.9% |
| Epoch Capabilities Index | 135.01 | 153.45 |
| SimpleBench | — | 45.8% |
| NYT Connections (extended) | — | 83.6% |
| CritPt | 0% | — |
| EnigmaEval | — | 10.4% |
| EBR-Bench | — | 23% |
| ForecastBench | — | 60.1 |
Math GPT-5.2 leads
GPT-4.1 mini: 23.1 (#264), GPT-5.2: 59.8 (#32)
| Benchmark | GPT-4.1 mini | GPT-5.2 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 6.7% | 67.4% |
| OTIS Mock AIME 2024-2025 | 44.7% | 96.1% |
| LMArena Math | 1343 | 1439 |
| FrontierMath (Feb 2025 set) | 4.5% | 40.7% |
| FrontierMath Tier 4 | — | 31.7% |
| MathArena Final-Answer Competitions | — | 72% |
| ProofBench | — | 15% |
| Omni-MATH | 49.1% | — |
| MATH Level 5 | 87.3% | — |
| FrontierMath Tier 4 (v1) | — | 18.8% |
Knowledge GPT-5.2 leads
GPT-4.1 mini: 34.7 (#183), GPT-5.2: 59.2 (#29)
| Benchmark | GPT-4.1 mini | GPT-5.2 |
|---|---|---|
| GPQA Diamond | 65.8% | 91.4% |
| SimpleQA Verified | 12.7% | 37.1% |
| LMArena Expert | 1338 | 1445 |
| Humanity's Last Exam | — | 27.8% |
| MMLU-Pro | 78.3% | — |
| Vectara Hallucination Rate | — | 8.4% |
| GPQA (HELM) | 61.4% | — |
Multimodal GPT-5.2 leads
GPT-4.1 mini: 35.2 (#77), GPT-5.2: 50.9 (#7)
| Benchmark | GPT-4.1 mini | GPT-5.2 |
|---|---|---|
| LMArena Vision | 1181 | 1268 |
| VPCT | — | 84% |
| Furniture Assembly | — | 38.3% |
| LMArena Document | — | 1405 |
Multilingual GPT-5.2 leads
GPT-4.1 mini: 45.9 (#161), GPT-5.2: 53.6 (#63)
| Benchmark | GPT-4.1 mini | GPT-5.2 |
|---|---|---|
| LMArena Non-English | 1318 | 1425 |
| LMArena Chinese | 1329 | 1460 |
| LMArena French | 1357 | 1456 |
| LMArena German | 1349 | 1448 |
| LMArena Japanese | 1291 | 1421 |
| LMArena Korean | 1298 | 1390 |
| LMArena Russian | 1324 | 1440 |
| LMArena Spanish | 1319 | 1433 |
Instruction Following GPT-5.2 leads
GPT-4.1 mini: 73.9 (#113), GPT-5.2: 74.9 (#83)
| Benchmark | GPT-4.1 mini | GPT-5.2 |
|---|---|---|
| LMArena Instruction Following | 1332 | 1417 |
| IFEval | 90.4% | — |
Long Context GPT-5.2 leads
GPT-4.1 mini: 31.8 (#270), GPT-5.2: 44.0 (#74)
| Benchmark | GPT-4.1 mini | GPT-5.2 |
|---|---|---|
| LMArena Longer Query | 1344 | 1428 |
| Fiction.LiveBench | 44.4% | — |
| CL-bench | — | 18.2% |
Writing & Preference GPT-5.2 leads
GPT-4.1 mini: 48.8 (#193), GPT-5.2: 67.0 (#30)
| Benchmark | GPT-4.1 mini | GPT-5.2 |
|---|---|---|
| LMArena Text | 1341 | 1439 |
| LMArena Creative Writing | 1300 | 1402 |
| EQ-Bench Creative Writing | 1147 | 1703 |
| LMArena Multi-Turn | 1354 | 1458 |
| WildBench | 83.8% | — |
Frequently asked questions
Is GPT-4.1 mini better than GPT-5.2?
GPT-5.2 is the stronger model overall, scoring 54.1 to 33.5 on the Noometry Index. GPT-4.1 mini costs 6.9× less per token, which makes it the better buy when GPT-5.2's lead doesn't matter for your workload.
Which is cheaper, GPT-4.1 mini or GPT-5.2?
GPT-4.1 mini is cheaper. It lists at $0.40 per million input tokens and $1.60 per million output tokens; GPT-5.2 lists at $1.75 and $14.
Is GPT-4.1 mini or GPT-5.2 better for coding?
GPT-5.2 scores higher on coding benchmarks: 52.2 versus 30.4 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-5.2 share?
35 benchmarks have published results for both models. GPT-4.1 mini has 47 scored results on Noometry and GPT-5.2 has 67.