Model comparison
GPT-4.1 mini vs o1
o1 is the stronger model overall, scoring 40.9 to 33.6 on the Noometry Index. GPT-4.1 mini costs 37× less per token, which makes it the better buy when o1's lead doesn't matter for your workload.
Last verified . 33 shared benchmarks.
Summary
- They share 33 benchmarks with published results for both. GPT-4.1 mini scores higher in 2 categories and o1 in 8 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in long context, where o1 leads 50.3 to 31.8.
- The biggest single-benchmark swing is CadEval: 16% for GPT-4.1 mini and 56% for o1.
- GPT-4.1 mini is cheaper at $0.40 / $1.60 per million input/output tokens, against $15 / $60 for o1.
- GPT-4.1 mini accepts more context: 1.05M tokens versus 200K.
Side by side
| GPT-4.1 mini | o1 | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 33.6 | 40.9 |
| Released | 2025-04-14 | 2024-09-12 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 200K |
| Max output | 33K | 100K |
| Input $ / M tokens | $0.40 | $15 |
| Output $ / M tokens | $1.60 | $60 |
| Results tracked | 47 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o1 leads
GPT-4.1 mini: 30.6 (#293), o1: 46.1 (#70)
| Benchmark | GPT-4.1 mini | o1 |
|---|---|---|
| Aider Polyglot | 32.4% | 61.7% |
| WeirdML | 37.6% | 47.6% |
| LMArena Coding | 1367 | 1367 |
| CadEval | 16% | 56% |
| SWE-bench Verified (bash only) | 23.9% | — |
| SciCode | 40.4% | — |
| BigCodeBench Instruct | 48.9% | — |
| LiveBench Coding | — | 69.7% |
| HumanEval+ | — | 89% |
| MBPP+ | — | 80.2% |
Agentic & Tool Use GPT-4.1 mini leads
GPT-4.1 mini: 33.3 (#55), o1: 24.6 (#117)
| Benchmark | GPT-4.1 mini | o1 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 50.5% | — |
| Cybench | — | 10% |
| METR Time Horizons | — | 51.1% |
Reasoning o1 leads
GPT-4.1 mini: 10.8 (#340), o1: 27.9 (#111)
| Benchmark | GPT-4.1 mini | o1 |
|---|---|---|
| ARC-AGI-1 | 3.5% | 30.7% |
| Chess Puzzles | 7% | 15% |
| LMArena Hard Prompts | 1349 | 1371 |
| DTBench | 68.8% | 74.7% |
| LMCA | 21.1% | 22.3% |
| Epoch Capabilities Index | 135.01 | 141.91 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | — | 41.7% |
| Kagi LLM Benchmark | 48.6% | — |
| CritPt | 0% | — |
| EnigmaEval | — | 5.7% |
| LiveBench Reasoning | — | 91.6% |
| Mystery Game Puzzles | 7% | — |
| LiveBench Data Analysis | — | 65.5% |
| LiveBench | — | 75.7% |
Math o1 leads
GPT-4.1 mini: 24.1 (#270), o1: 36.1 (#175)
| Benchmark | GPT-4.1 mini | o1 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 6.7% | 14.7% |
| OTIS Mock AIME 2024-2025 | 44.7% | 73.3% |
| LMArena Math | 1343 | 1388 |
| MATH Level 5 | 87.3% | 94.7% |
| FrontierMath (Feb 2025 set) | 4.5% | 9.3% |
| Omni-MATH | 49.1% | — |
| LiveBench Math | — | 80.3% |
Knowledge o1 leads
GPT-4.1 mini: 34.7 (#194), o1: 41.5 (#110)
| Benchmark | GPT-4.1 mini | o1 |
|---|---|---|
| GPQA Diamond | 65.8% | 76.8% |
| SimpleQA Verified | 12.7% | 41.1% |
| LMArena Expert | 1338 | 1361 |
| Humanity's Last Exam | — | 8% |
| MMLU-Pro | 78.3% | — |
| Confabulations | — | 11.7% |
| GPQA (HELM) | 61.4% | — |
Multimodal GPT-4.1 mini leads
GPT-4.1 mini: 35.8 (#82), o1: 34.2 (#93)
| Benchmark | GPT-4.1 mini | o1 |
|---|---|---|
| LMArena Vision | 1181 | 1168 |
| GeoBench | — | 80% |
| VPCT | — | 37% |
| SpatialViz-Bench | — | 41.4% |
Multilingual o1 leads
GPT-4.1 mini: 45.7 (#166), o1: 48.6 (#142)
| Benchmark | GPT-4.1 mini | o1 |
|---|---|---|
| LMArena Non-English | 1318 | 1358 |
| LMArena Chinese | 1329 | 1394 |
| LMArena French | 1358 | 1344 |
| LMArena German | 1351 | 1337 |
| LMArena Japanese | 1290 | 1346 |
| LMArena Korean | 1298 | 1396 |
| LMArena Russian | 1324 | 1356 |
| LMArena Spanish | 1319 | 1345 |
Instruction Following o1 leads
GPT-4.1 mini: 73.7 (#118), o1: 74.8 (#86)
| Benchmark | GPT-4.1 mini | o1 |
|---|---|---|
| LMArena Instruction Following | 1333 | 1367 |
| LiveBench Instruction Following | — | 81.5% |
| IFEval | 90.4% | — |
Long Context o1 leads
GPT-4.1 mini: 31.8 (#275), o1: 50.3 (#9)
| Benchmark | GPT-4.1 mini | o1 |
|---|---|---|
| Fiction.LiveBench | 44.4% | 83.3% |
| LMArena Longer Query | 1344 | 1378 |
Writing & Preference o1 leads
GPT-4.1 mini: 48.6 (#199), o1: 55.6 (#144)
| Benchmark | GPT-4.1 mini | o1 |
|---|---|---|
| LMArena Text | 1340 | 1366 |
| LMArena Creative Writing | 1300 | 1348 |
| LMArena Multi-Turn | 1354 | 1369 |
| Short-Story Creative Writing | — | 70.2% |
| EQ-Bench Creative Writing | 1147 | — |
| WildBench | 83.8% | — |
| LiveBench Language | — | 65.4% |
Frequently asked questions
Is GPT-4.1 mini better than o1?
o1 is the stronger model overall, scoring 40.9 to 33.6 on the Noometry Index. GPT-4.1 mini costs 37× less per token, which makes it the better buy when o1's lead doesn't matter for your workload.
Which is cheaper, GPT-4.1 mini or o1?
GPT-4.1 mini is cheaper. It lists at $0.40 per million input tokens and $1.60 per million output tokens; o1 lists at $15 and $60.
Is GPT-4.1 mini or o1 better for coding?
o1 scores higher on coding benchmarks: 46.1 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 o1 share?
33 benchmarks have published results for both models. GPT-4.1 mini has 47 scored results on Noometry and o1 has 52.