Model comparison
GPT-4.1 mini vs o4-mini
o4-mini is the stronger model overall, scoring 41.6 to 33.6 on the Noometry Index. GPT-4.1 mini costs 2.8× less per token, which makes it the better buy when o4-mini's lead doesn't matter for your workload.
Last verified . 44 shared benchmarks.
Summary
- They share 44 benchmarks with published results for both. GPT-4.1 mini scores higher in 1 category and o4-mini in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where o4-mini leads 40.8 to 24.1.
- The biggest single-benchmark swing is ARC-AGI-1: 3.5% for GPT-4.1 mini and 58.7% for o4-mini.
- GPT-4.1 mini is cheaper at $0.40 / $1.60 per million input/output tokens, against $1.10 / $4.40 for o4-mini.
- GPT-4.1 mini accepts more context: 1.05M tokens versus 200K.
Side by side
| GPT-4.1 mini | o4-mini | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 33.6 | 41.6 |
| Released | 2025-04-14 | 2025-04-16 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 200K |
| Max output | 33K | 100K |
| Input $ / M tokens | $0.40 | $1.10 |
| Output $ / M tokens | $1.60 | $4.40 |
| Results tracked | 47 | 60 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o4-mini leads
GPT-4.1 mini: 30.6 (#293), o4-mini: 40.9 (#127)
| Benchmark | GPT-4.1 mini | o4-mini |
|---|---|---|
| SWE-bench Verified (bash only) | 23.9% | 45% |
| Aider Polyglot | 32.4% | 72% |
| WeirdML | 37.6% | 52.6% |
| LMArena Coding | 1367 | 1368 |
| CadEval | 16% | 62% |
| SciCode | 40.4% | — |
| GSO | — | 3.6% |
| BigCodeBench Instruct | 48.9% | — |
| ALE-Bench | — | 826.17 |
| AlgoTune | — | 1.72 |
Agentic & Tool Use Too close to call
GPT-4.1 mini: 33.3 (#55), o4-mini: 32.6 (#61)
| Benchmark | GPT-4.1 mini | o4-mini |
|---|---|---|
| Berkeley Function Calling Leaderboard | 50.5% | 53.2% |
| GDPval | — | 25.3% |
| METR Time Horizons | — | 63.9% |
Reasoning o4-mini leads
GPT-4.1 mini: 10.8 (#340), o4-mini: 24.6 (#162)
| Benchmark | GPT-4.1 mini | o4-mini |
|---|---|---|
| ARC-AGI-2 | 0% | 6.1% |
| Kagi LLM Benchmark | 48.6% | 67.6% |
| ARC-AGI-1 | 3.5% | 58.7% |
| CritPt | 0% | 0.6% |
| Chess Puzzles | 7% | 26% |
| LMArena Hard Prompts | 1349 | 1351 |
| Mystery Game Puzzles | 7% | 5% |
| DTBench | 68.8% | 77.6% |
| LMCA | 21.1% | 26.5% |
| Epoch Capabilities Index | 135.01 | 145.64 |
| SimpleBench | — | 38.7% |
| EnigmaEval | — | 9.2% |
| ForecastBench | — | 61.8 |
Math o4-mini leads
GPT-4.1 mini: 24.1 (#270), o4-mini: 40.8 (#89)
| Benchmark | GPT-4.1 mini | o4-mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 6.7% | 36.1% |
| OTIS Mock AIME 2024-2025 | 44.7% | 81.7% |
| Omni-MATH | 49.1% | 72% |
| LMArena Math | 1343 | 1389 |
| MATH Level 5 | 87.3% | 97.8% |
| FrontierMath (Feb 2025 set) | 4.5% | 24.8% |
| FrontierMath Tier 4 | — | 4.9% |
| FrontierMath Tier 4 (v1) | — | 6.3% |
Knowledge o4-mini leads
GPT-4.1 mini: 34.7 (#194), o4-mini: 43.6 (#91)
| Benchmark | GPT-4.1 mini | o4-mini |
|---|---|---|
| GPQA Diamond | 65.8% | 79.6% |
| SimpleQA Verified | 12.7% | 19.6% |
| MMLU-Pro | 78.3% | 82% |
| GPQA (HELM) | 61.4% | 73.5% |
| LMArena Expert | 1338 | 1343 |
| Humanity's Last Exam | — | 18.1% |
| Confabulations | — | 15.8% |
| Vectara Hallucination Rate | — | 18.6% |
Multimodal o4-mini leads
GPT-4.1 mini: 35.8 (#82), o4-mini: 40.2 (#49)
| Benchmark | GPT-4.1 mini | o4-mini |
|---|---|---|
| LMArena Vision | 1181 | 1194 |
| GeoBench | — | 64% |
| VPCT | — | 57.5% |
Multilingual o4-mini leads
GPT-4.1 mini: 45.7 (#166), o4-mini: 47.0 (#154)
| Benchmark | GPT-4.1 mini | o4-mini |
|---|---|---|
| LMArena Non-English | 1318 | 1337 |
| LMArena Chinese | 1329 | 1354 |
| LMArena French | 1358 | 1364 |
| LMArena German | 1351 | 1336 |
| LMArena Japanese | 1290 | 1308 |
| LMArena Korean | 1298 | 1312 |
| LMArena Russian | 1324 | 1334 |
| LMArena Spanish | 1319 | 1347 |
Instruction Following o4-mini leads
GPT-4.1 mini: 73.7 (#118), o4-mini: 75.2 (#68)
| Benchmark | GPT-4.1 mini | o4-mini |
|---|---|---|
| IFEval | 90.4% | 92.8% |
| LMArena Instruction Following | 1333 | 1321 |
Long Context o4-mini leads
GPT-4.1 mini: 31.8 (#275), o4-mini: 45.5 (#33)
| Benchmark | GPT-4.1 mini | o4-mini |
|---|---|---|
| Fiction.LiveBench | 44.4% | 77.8% |
| LMArena Longer Query | 1344 | 1315 |
Writing & Preference o4-mini leads
GPT-4.1 mini: 48.6 (#199), o4-mini: 54.0 (#152)
| Benchmark | GPT-4.1 mini | o4-mini |
|---|---|---|
| LMArena Text | 1340 | 1353 |
| LMArena Creative Writing | 1300 | 1294 |
| WildBench | 83.8% | 85.4% |
| LMArena Multi-Turn | 1354 | 1350 |
| Short-Story Creative Writing | — | 75% |
| EQ-Bench Creative Writing | 1147 | — |
Frequently asked questions
Is GPT-4.1 mini better than o4-mini?
o4-mini is the stronger model overall, scoring 41.6 to 33.6 on the Noometry Index. GPT-4.1 mini costs 2.8× less per token, which makes it the better buy when o4-mini's lead doesn't matter for your workload.
Which is cheaper, GPT-4.1 mini or o4-mini?
GPT-4.1 mini is cheaper. It lists at $0.40 per million input tokens and $1.60 per million output tokens; o4-mini lists at $1.10 and $4.40.
Is GPT-4.1 mini or o4-mini better for coding?
o4-mini scores higher on coding benchmarks: 40.9 versus 30.6 in the Noometry coding category.
Which has the bigger context window?
GPT-4.1 mini does, with 1.05M tokens against 200K.
How many benchmarks do GPT-4.1 mini and o4-mini share?
44 benchmarks have published results for both models. GPT-4.1 mini has 47 scored results on Noometry and o4-mini has 60.