Model comparison
GPT-5 vs o1-mini
GPT-5 is the stronger model overall, scoring 50.9 to 33.7 on the Noometry Index.
Last verified . 29 shared benchmarks.
Summary
- They share 29 benchmarks with published results for both. GPT-5 scores higher in 9 categories and o1-mini in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5 leads 38.3 to 8.9.
- The biggest single-benchmark swing is Aider Polyglot: 88% for GPT-5 and 32.9% for o1-mini.
Side by side
| GPT-5 | o1-mini | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 50.9 | 33.7 |
| Released | 2025-08-07 | 2024-09-12 |
| Weights | Proprietary | Proprietary |
| Context window | 400K | — |
| Max output | 128K | — |
| Input $ / M tokens | $1.25 | — |
| Output $ / M tokens | $10 | — |
| Results tracked | 69 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5 leads
GPT-5: 50.7 (#39), o1-mini: 35.1 (#218)
| Benchmark | GPT-5 | o1-mini |
|---|---|---|
| Aider Polyglot | 88% | 32.9% |
| WeirdML | 60.7% | 36.3% |
| LMArena Coding | 1436 | 1362 |
| SWE-bench Verified | 73.6% | — |
| SWE-bench Verified (bash only) | 65% | — |
| LMArena WebDev | 1417 | — |
| SciCode | 42.9% | — |
| GSO | 6.9% | — |
| LiveBench Coding | — | 48% |
| ALE-Bench | 1,162 | — |
| AlgoTune | 1.67 | — |
| HumanEval+ | — | 89% |
| MBPP+ | — | 78.8% |
Agentic & Tool Use GPT-5 leads
GPT-5: 33.0 (#53), o1-mini: 24.3 (#112)
| Benchmark | GPT-5 | o1-mini |
|---|---|---|
| Terminal-Bench | 49.6% | — |
| GDPval | 34.8% | — |
| Remote Labor Index | 1.7% | — |
| Cybench | — | 10% |
| DeepResearch Bench | 49.6% | — |
| BALROG | 32.8% | — |
| LMArena Search | 1133 | — |
| METR Time Horizons | 69.6% | — |
Reasoning GPT-5 leads
GPT-5: 38.3 (#55), o1-mini: 8.9 (#340)
| Benchmark | GPT-5 | o1-mini |
|---|---|---|
| ARC-AGI-2 | 9.9% | 0.8% |
| SimpleBench | 56.7% | 18.1% |
| ARC-AGI-1 | 65.7% | 14% |
| LMArena Hard Prompts | 1415 | 1333 |
| Epoch Capabilities Index | 150 | 135.82 |
| Kagi LLM Benchmark | 72.7% | — |
| CritPt | 12.6% | — |
| Chess Puzzles | 37% | — |
| EnigmaEval | 10.5% | — |
| EBR-Bench | 12.7% | — |
| LiveBench Reasoning | — | 72.3% |
| Mystery Game Puzzles | 23% | — |
| DTBench | 90.7% | — |
| LiveBench Data Analysis | — | 57.9% |
| LMCA | 40% | — |
| ForecastBench | 61.4 | — |
| LiveBench | — | 57.8% |
Math GPT-5 leads
GPT-5: 54.6 (#36), o1-mini: 33.7 (#168)
| Benchmark | GPT-5 | o1-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 91.4% | 46.9% |
| LMArena Math | 1406 | 1358 |
| MATH Level 5 | 98.1% | 89.2% |
| FrontierMath (Feb 2025 set) | 32.4% | 1.7% |
| FrontierMath (Tiers 1-3) | 55.4% | — |
| FrontierMath Tier 4 | 22% | — |
| ProofBench | 18% | — |
| Omni-MATH | 64.7% | — |
| LiveBench Math | — | 62% |
| FrontierMath Tier 4 (v1) | 12.5% | — |
Knowledge GPT-5 leads
GPT-5: 56.5 (#37), o1-mini: 34.8 (#180)
| Benchmark | GPT-5 | o1-mini |
|---|---|---|
| GPQA Diamond | 86.2% | 62.4% |
| Confabulations | 10.3% | 18.6% |
| LMArena Expert | 1420 | 1316 |
| Humanity's Last Exam | 25.3% | — |
| SimpleQA Verified | 50.1% | — |
| MMLU-Pro | 86.3% | — |
| Vectara Hallucination Rate | 14.7% | — |
| GPQA (HELM) | 79.2% | — |
Multimodal Not comparable
GPT-5: 46.1 (#12), o1-mini: —
| Benchmark | GPT-5 | o1-mini |
|---|---|---|
| LMArena Vision | 1232 | — |
| GeoBench | 81% | — |
| VPCT | 66% | — |
Multilingual GPT-5 leads
GPT-5: 51.5 (#105), o1-mini: 43.8 (#177)
| Benchmark | GPT-5 | o1-mini |
|---|---|---|
| LMArena Non-English | 1397 | 1289 |
| LMArena Chinese | 1423 | 1314 |
| LMArena French | 1409 | 1292 |
| LMArena German | 1415 | 1278 |
| LMArena Japanese | 1411 | 1245 |
| LMArena Korean | 1361 | 1223 |
| LMArena Russian | 1406 | 1283 |
| LMArena Spanish | 1398 | 1302 |
Instruction Following GPT-5 leads
GPT-5: 74.0 (#107), o1-mini: 67.0 (#200)
| Benchmark | GPT-5 | o1-mini |
|---|---|---|
| LMArena Instruction Following | 1388 | 1304 |
| LiveBench Instruction Following | — | 65.4% |
| IFEval | 87.5% | — |
Long Context GPT-5 leads
GPT-5: 69.5 (#2), o1-mini: 40.1 (#156)
| Benchmark | GPT-5 | o1-mini |
|---|---|---|
| LMArena Longer Query | 1399 | 1321 |
| Fiction.LiveBench | 97.2% | — |
Writing & Preference GPT-5 leads
GPT-5: 63.5 (#63), o1-mini: 48.6 (#196)
| Benchmark | GPT-5 | o1-mini |
|---|---|---|
| LMArena Text | 1406 | 1317 |
| LMArena Creative Writing | 1365 | 1244 |
| Short-Story Creative Writing | 86% | 64.9% |
| LMArena Multi-Turn | 1426 | 1314 |
| EQ-Bench Creative Writing | 1627 | — |
| WildBench | 85.7% | — |
| LiveBench Language | — | 40.9% |
Frequently asked questions
Is GPT-5 better than o1-mini?
GPT-5 is the stronger model overall, scoring 50.9 to 33.7 on the Noometry Index.
Is GPT-5 or o1-mini better for coding?
GPT-5 scores higher on coding benchmarks: 50.7 versus 35.1 in the Noometry coding category.
How many benchmarks do GPT-5 and o1-mini share?
29 benchmarks have published results for both models. GPT-5 has 69 scored results on Noometry and o1-mini has 39.