Model comparison
GPT-4.1 vs GPT-4o mini
GPT-4.1 is the stronger model overall, scoring 35.9 to 25.5 on the Noometry Index. GPT-4o mini costs 13× less per token, which makes it the better buy when GPT-4.1's lead doesn't matter for your workload.
Last verified . 39 shared benchmarks.
Summary
- They share 39 benchmarks with published results for both. GPT-4.1 scores higher in 10 categories and GPT-4o mini in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-4.1 leads 37.1 to 17.7.
- The biggest single-benchmark swing is Aider Polyglot: 52.4% for GPT-4.1 and 3.6% for GPT-4o mini.
- GPT-4o mini is cheaper at $0.15 / $0.60 per million input/output tokens, against $2 / $8 for GPT-4.1.
- GPT-4.1 accepts more context: 1.05M tokens versus 128K.
Side by side
| GPT-4.1 | GPT-4o mini | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 35.9 | 25.5 |
| Released | 2025-04-14 | 2024-07-18 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 128K |
| Max output | 33K | 16K |
| Input $ / M tokens | $2 | $0.15 |
| Output $ / M tokens | $8 | $0.60 |
| Results tracked | 52 | 60 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-4.1 leads
GPT-4.1: 34.4 (#238), GPT-4o mini: 22.0 (#335)
| Benchmark | GPT-4.1 | GPT-4o mini |
|---|---|---|
| Aider Polyglot | 52.4% | 3.6% |
| WeirdML | 39% | 11.8% |
| LMArena Coding | 1391 | 1290 |
| SWE-bench Verified | 48.5% | — |
| SWE-bench Verified (bash only) | 39.6% | — |
| BigCodeBench Instruct | — | 46.1% |
| LiveBench Coding | — | 43.1% |
| BigCodeBench Complete | — | 57.4% |
| CadEval | 42% | — |
| ALE-Bench | 558.1 | — |
| HumanEval+ | — | 83.5% |
| MBPP+ | — | 72.2% |
Agentic & Tool Use GPT-4.1 leads
GPT-4.1: 34.7 (#43), GPT-4o mini: 27.5 (#101)
| Benchmark | GPT-4.1 | GPT-4o mini |
|---|---|---|
| Berkeley Function Calling Leaderboard | 54% | — |
| BALROG | — | 17.4% |
Reasoning GPT-4.1 leads
GPT-4.1: 11.7 (#339), GPT-4o mini: 8.7 (#347)
| Benchmark | GPT-4.1 | GPT-4o mini |
|---|---|---|
| ARC-AGI-2 | 0.4% | 0% |
| SimpleBench | 27% | 10.7% |
| Kagi LLM Benchmark | 52.3% | 28.8% |
| Chess Puzzles | 6% | 0% |
| LMArena Hard Prompts | 1384 | 1267 |
| DTBench | 68.3% | 54.4% |
| LMCA | 25.6% | 10.4% |
| Epoch Capabilities Index | 136.78 | 126.56 |
| ARC-AGI-1 | 5.5% | — |
| EnigmaEval | 2.2% | — |
| LiveBench Reasoning | — | 32.8% |
| Mystery Game Puzzles | — | 12% |
| LiveBench Data Analysis | — | 50% |
| ForecastBench | 61.5 | — |
| LiveBench | — | 41.3% |
| PIQA | — | 88.7% |
Math GPT-4.1 leads
GPT-4.1: 22.3 (#280), GPT-4o mini: 10.4 (#314)
| Benchmark | GPT-4.1 | GPT-4o mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 6% | 0.7% |
| OTIS Mock AIME 2024-2025 | 38.3% | 6.9% |
| Omni-MATH | 47.1% | 28% |
| LMArena Math | 1370 | 1267 |
| MATH Level 5 | 83% | 52.6% |
| LiveBench Math | — | 36.3% |
| FrontierMath (Feb 2025 set) | 5.5% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
| GSM8K | — | 91.3% |
Knowledge GPT-4.1 leads
GPT-4.1: 37.1 (#160), GPT-4o mini: 17.7 (#284)
| Benchmark | GPT-4.1 | GPT-4o mini |
|---|---|---|
| GPQA Diamond | 66.9% | 37.7% |
| SimpleQA Verified | 31.1% | 8.3% |
| MMLU-Pro | 81.1% | 60.3% |
| GPQA (HELM) | 65.9% | 36.8% |
| LMArena Expert | 1364 | 1235 |
| Humanity's Last Exam | 5.4% | — |
| Confabulations | — | 37.2% |
| Vectara Hallucination Rate | 5.6% | — |
| BoolQ | — | 88.7% |
| MMLU | — | 81.8% |
Multimodal GPT-4.1 leads
GPT-4.1: 38.2 (#67), GPT-4o mini: 25.9 (#122)
| Benchmark | GPT-4.1 | GPT-4o mini |
|---|---|---|
| LMArena Vision | 1211 | 1066 |
| GeoBench | 72% | 64% |
| Video-MME | — | 64.8% |
| VPCT | — | 34% |
Multilingual GPT-4.1 leads
GPT-4.1: 49.4 (#133), GPT-4o mini: 42.0 (#199)
| Benchmark | GPT-4.1 | GPT-4o mini |
|---|---|---|
| LMArena Non-English | 1370 | 1266 |
| LMArena Chinese | 1382 | 1265 |
| LMArena French | 1382 | 1297 |
| LMArena German | 1381 | 1272 |
| LMArena Japanese | 1319 | 1216 |
| LMArena Korean | 1339 | 1195 |
| LMArena Russian | 1377 | 1275 |
| LMArena Spanish | 1376 | 1276 |
Instruction Following GPT-4.1 leads
GPT-4.1: 71.3 (#153), GPT-4o mini: 61.9 (#239)
| Benchmark | GPT-4.1 | GPT-4o mini |
|---|---|---|
| IFEval | 83.8% | 78.2% |
| LMArena Instruction Following | 1367 | 1258 |
| LiveBench Instruction Following | — | 56.8% |
Long Context Too close to call
GPT-4.1: 40.0 (#163), GPT-4o mini: 39.1 (#186)
| Benchmark | GPT-4.1 | GPT-4o mini |
|---|---|---|
| LMArena Longer Query | 1385 | 1289 |
| Fiction.LiveBench | 63.9% | — |
Writing & Preference GPT-4.1 leads
GPT-4.1: 57.6 (#125), GPT-4o mini: 39.5 (#248)
| Benchmark | GPT-4.1 | GPT-4o mini |
|---|---|---|
| LMArena Text | 1383 | 1286 |
| LMArena Creative Writing | 1363 | 1268 |
| EQ-Bench Creative Writing | 1420 | 873 |
| WildBench | 85.4% | 79.1% |
| LMArena Multi-Turn | 1398 | 1285 |
| Short-Story Creative Writing | — | 67.2% |
| LiveBench Language | — | 28.6% |
Frequently asked questions
Is GPT-4.1 better than GPT-4o mini?
GPT-4.1 is the stronger model overall, scoring 35.9 to 25.5 on the Noometry Index. GPT-4o mini costs 13× less per token, which makes it the better buy when GPT-4.1's lead doesn't matter for your workload.
Which is cheaper, GPT-4.1 or GPT-4o mini?
GPT-4o mini is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; GPT-4.1 lists at $2 and $8.
Is GPT-4.1 or GPT-4o mini better for coding?
GPT-4.1 scores higher on coding benchmarks: 34.4 versus 22.0 in the Noometry coding category.
Which has the bigger context window?
GPT-4.1 does, with 1.05M tokens against 128K.
How many benchmarks do GPT-4.1 and GPT-4o mini share?
39 benchmarks have published results for both models. GPT-4.1 has 52 scored results on Noometry and GPT-4o mini has 60.