Model comparison
GPT-4.1 vs o1-mini
GPT-4.1 is the stronger model overall, scoring 35.9 to 34.0 on the Noometry Index.
Last verified . 27 shared benchmarks.
Summary
- They share 27 benchmarks with published results for both. GPT-4.1 scores higher in 6 categories and o1-mini in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where o1-mini leads 35.4 to 22.3.
- The biggest single-benchmark swing is Aider Polyglot: 52.4% for GPT-4.1 and 32.9% for o1-mini.
Side by side
| GPT-4.1 | o1-mini | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 35.9 | 34.0 |
| Released | 2025-04-14 | 2024-09-12 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | — |
| Max output | 33K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $8 | — |
| Results tracked | 52 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o1-mini leads
GPT-4.1: 34.4 (#238), o1-mini: 35.5 (#224)
| Benchmark | GPT-4.1 | o1-mini |
|---|---|---|
| Aider Polyglot | 52.4% | 32.9% |
| WeirdML | 39% | 36.3% |
| LMArena Coding | 1391 | 1362 |
| SWE-bench Verified | 48.5% | — |
| SWE-bench Verified (bash only) | 39.6% | — |
| LiveBench Coding | — | 48% |
| CadEval | 42% | — |
| ALE-Bench | 558.1 | — |
| HumanEval+ | — | 89% |
| MBPP+ | — | 78.8% |
Agentic & Tool Use GPT-4.1 leads
GPT-4.1: 34.7 (#43), o1-mini: 24.6 (#118)
| Benchmark | GPT-4.1 | o1-mini |
|---|---|---|
| Berkeley Function Calling Leaderboard | 54% | — |
| Cybench | — | 10% |
Reasoning GPT-4.1 leads
GPT-4.1: 11.7 (#339), o1-mini: 8.8 (#346)
| Benchmark | GPT-4.1 | o1-mini |
|---|---|---|
| ARC-AGI-2 | 0.4% | 0.8% |
| SimpleBench | 27% | 18.1% |
| ARC-AGI-1 | 5.5% | 14% |
| LMArena Hard Prompts | 1384 | 1333 |
| Epoch Capabilities Index | 136.78 | 135.82 |
| Kagi LLM Benchmark | 52.3% | — |
| Chess Puzzles | 6% | — |
| EnigmaEval | 2.2% | — |
| LiveBench Reasoning | — | 72.3% |
| DTBench | 68.3% | — |
| LiveBench Data Analysis | — | 57.9% |
| LMCA | 25.6% | — |
| ForecastBench | 61.5 | — |
| LiveBench | — | 57.8% |
Math o1-mini leads
GPT-4.1: 22.3 (#280), o1-mini: 35.4 (#186)
| Benchmark | GPT-4.1 | o1-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 38.3% | 46.9% |
| LMArena Math | 1370 | 1358 |
| MATH Level 5 | 83% | 89.2% |
| FrontierMath (Feb 2025 set) | 5.5% | 1.7% |
| FrontierMath (Tiers 1-3) | 6% | — |
| Omni-MATH | 47.1% | — |
| LiveBench Math | — | 62% |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge GPT-4.1 leads
GPT-4.1: 37.1 (#160), o1-mini: 34.9 (#192)
| Benchmark | GPT-4.1 | o1-mini |
|---|---|---|
| GPQA Diamond | 66.9% | 62.4% |
| LMArena Expert | 1364 | 1316 |
| Humanity's Last Exam | 5.4% | — |
| SimpleQA Verified | 31.1% | — |
| MMLU-Pro | 81.1% | — |
| Confabulations | — | 18.6% |
| Vectara Hallucination Rate | 5.6% | — |
| GPQA (HELM) | 65.9% | — |
Multimodal Not comparable
GPT-4.1: 38.2 (#67), o1-mini: —
| Benchmark | GPT-4.1 | o1-mini |
|---|---|---|
| LMArena Vision | 1211 | — |
| GeoBench | 72% | — |
Multilingual GPT-4.1 leads
GPT-4.1: 49.4 (#133), o1-mini: 43.6 (#182)
| Benchmark | GPT-4.1 | o1-mini |
|---|---|---|
| LMArena Non-English | 1370 | 1289 |
| LMArena Chinese | 1382 | 1314 |
| LMArena French | 1382 | 1293 |
| LMArena German | 1381 | 1278 |
| LMArena Japanese | 1319 | 1245 |
| LMArena Korean | 1339 | 1223 |
| LMArena Russian | 1377 | 1283 |
| LMArena Spanish | 1376 | 1303 |
Instruction Following GPT-4.1 leads
GPT-4.1: 71.3 (#153), o1-mini: 66.7 (#206)
| Benchmark | GPT-4.1 | o1-mini |
|---|---|---|
| LMArena Instruction Following | 1367 | 1304 |
| LiveBench Instruction Following | — | 65.4% |
| IFEval | 83.8% | — |
Long Context Too close to call
GPT-4.1: 40.0 (#163), o1-mini: 40.1 (#161)
| Benchmark | GPT-4.1 | o1-mini |
|---|---|---|
| LMArena Longer Query | 1385 | 1320 |
| Fiction.LiveBench | 63.9% | — |
Writing & Preference GPT-4.1 leads
GPT-4.1: 57.6 (#125), o1-mini: 48.4 (#202)
| Benchmark | GPT-4.1 | o1-mini |
|---|---|---|
| LMArena Text | 1383 | 1317 |
| LMArena Creative Writing | 1363 | 1244 |
| LMArena Multi-Turn | 1398 | 1314 |
| Short-Story Creative Writing | — | 64.9% |
| EQ-Bench Creative Writing | 1420 | — |
| WildBench | 85.4% | — |
| LiveBench Language | — | 40.9% |
Frequently asked questions
Is GPT-4.1 better than o1-mini?
GPT-4.1 is the stronger model overall, scoring 35.9 to 34.0 on the Noometry Index.
Is GPT-4.1 or o1-mini better for coding?
o1-mini scores higher on coding benchmarks: 35.5 versus 34.4 in the Noometry coding category.
How many benchmarks do GPT-4.1 and o1-mini share?
27 benchmarks have published results for both models. GPT-4.1 has 52 scored results on Noometry and o1-mini has 39.