Model comparison
GPT-5 vs o3-mini
GPT-5 is the stronger model overall, scoring 50.9 to 36.7 on the Noometry Index. o3-mini costs 1.8× less per token, which makes it the better buy when GPT-5's lead doesn't matter for your workload.
Last verified . 42 shared benchmarks.
Summary
- They share 42 benchmarks with published results for both. GPT-5 scores higher in 8 categories and o3-mini in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in long context, where GPT-5 leads 69.5 to 33.8.
- The biggest single-benchmark swing is Fiction.LiveBench: 97.2% for GPT-5 and 50% for o3-mini.
- o3-mini is cheaper at $1.10 / $4.40 per million input/output tokens, against $1.25 / $10 for GPT-5.
- GPT-5 accepts more context: 400K tokens versus 200K.
Side by side
| GPT-5 | o3-mini | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 50.9 | 36.7 |
| Released | 2025-08-07 | 2024-12-20 |
| Weights | Proprietary | Proprietary |
| Context window | 400K | 200K |
| Max output | 128K | 100K |
| Input $ / M tokens | $1.25 | $1.10 |
| Output $ / M tokens | $10 | $4.40 |
| Results tracked | 69 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5 leads
GPT-5: 50.3 (#47), o3-mini: 40.8 (#132)
| Benchmark | GPT-5 | o3-mini |
|---|---|---|
| Aider Polyglot | 88% | 60.4% |
| SciCode | 42.9% | 39.8% |
| GSO | 6.9% | 1.3% |
| WeirdML | 60.7% | 43.7% |
| LMArena Coding | 1436 | 1378 |
| SWE-bench Verified | 73.6% | — |
| SWE-bench Verified (bash only) | 65% | — |
| LMArena WebDev | 1418 | — |
| LiveBench Coding | — | 82.7% |
| CadEval | — | 54% |
| ALE-Bench | 1,162 | — |
| AlgoTune | 1.67 | — |
Agentic & Tool Use GPT-5 leads
GPT-5: 33.1 (#56), o3-mini: 29.6 (#84)
| Benchmark | GPT-5 | o3-mini |
|---|---|---|
| Terminal-Bench | 49.6% | — |
| GDPval | 34.8% | — |
| Remote Labor Index | 1.7% | — |
| Cybench | — | 22.5% |
| DeepResearch Bench | 49.6% | — |
| BALROG | 32.8% | — |
| LMArena Search | 1133 | — |
| METR Time Horizons | 69.6% | — |
Reasoning GPT-5 leads
GPT-5: 38.3 (#64), o3-mini: 16.3 (#305)
| Benchmark | GPT-5 | o3-mini |
|---|---|---|
| ARC-AGI-2 | 9.9% | 3% |
| SimpleBench | 56.7% | 22.8% |
| ARC-AGI-1 | 65.7% | 34.5% |
| CritPt | 12.6% | 0.3% |
| Chess Puzzles | 37% | 17% |
| LMArena Hard Prompts | 1416 | 1366 |
| Mystery Game Puzzles | 23% | 7% |
| DTBench | 90.7% | 68.8% |
| LMCA | 40% | 19% |
| Epoch Capabilities Index | 150 | 140.34 |
| ForecastBench | 61.4 | 59.6 |
| Kagi LLM Benchmark | 72.7% | — |
| EnigmaEval | 10.5% | — |
| EBR-Bench | 12.7% | — |
| LiveBench Reasoning | — | 89.6% |
| LiveBench Data Analysis | — | 70.6% |
| LiveBench | — | 75.9% |
Math GPT-5 leads
GPT-5: 55.0 (#44), o3-mini: 28.1 (#244)
| Benchmark | GPT-5 | o3-mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 55.4% | 18.6% |
| FrontierMath Tier 4 | 22% | 0% |
| OTIS Mock AIME 2024-2025 | 91.4% | 76.9% |
| LMArena Math | 1407 | 1396 |
| MATH Level 5 | 98.1% | 96.5% |
| FrontierMath (Feb 2025 set) | 32.4% | 12.4% |
| FrontierMath Tier 4 (v1) | 12.5% | 4.2% |
| ProofBench | 18% | — |
| Omni-MATH | 64.7% | — |
| LiveBench Math | — | 77.3% |
Knowledge GPT-5 leads
GPT-5: 56.6 (#43), o3-mini: 38.3 (#146)
| Benchmark | GPT-5 | o3-mini |
|---|---|---|
| GPQA Diamond | 86.2% | 77% |
| SimpleQA Verified | 50.1% | 15.3% |
| Confabulations | 10.3% | 17.9% |
| LMArena Expert | 1419 | 1364 |
| Humanity's Last Exam | 25.3% | — |
| MMLU-Pro | 86.3% | — |
| Vectara Hallucination Rate | 14.7% | — |
| GPQA (HELM) | 79.2% | — |
Multimodal Not comparable
GPT-5: 46.8 (#13), o3-mini: —
| Benchmark | GPT-5 | o3-mini |
|---|---|---|
| LMArena Vision | 1232 | — |
| GeoBench | 81% | — |
| VPCT | 66% | — |
Multilingual GPT-5 leads
GPT-5: 51.4 (#110), o3-mini: 45.7 (#164)
| Benchmark | GPT-5 | o3-mini |
|---|---|---|
| LMArena Non-English | 1397 | 1319 |
| LMArena Chinese | 1422 | 1379 |
| LMArena French | 1410 | 1334 |
| LMArena German | 1416 | 1303 |
| LMArena Japanese | 1409 | 1286 |
| LMArena Korean | 1360 | 1314 |
| LMArena Russian | 1406 | 1304 |
| LMArena Spanish | 1399 | 1321 |
Instruction Following o3-mini leads
GPT-5: 73.8 (#113), o3-mini: 75.1 (#72)
| Benchmark | GPT-5 | o3-mini |
|---|---|---|
| LMArena Instruction Following | 1388 | 1337 |
| LiveBench Instruction Following | — | 84.4% |
| IFEval | 87.5% | — |
Long Context GPT-5 leads
GPT-5: 69.5 (#2), o3-mini: 33.8 (#256)
| Benchmark | GPT-5 | o3-mini |
|---|---|---|
| Fiction.LiveBench | 97.2% | 50% |
| LMArena Longer Query | 1399 | 1343 |
Writing & Preference GPT-5 leads
GPT-5: 63.4 (#65), o3-mini: 50.3 (#182)
| Benchmark | GPT-5 | o3-mini |
|---|---|---|
| LMArena Text | 1406 | 1337 |
| LMArena Creative Writing | 1365 | 1286 |
| Short-Story Creative Writing | 86% | 61.7% |
| LMArena Multi-Turn | 1426 | 1320 |
| EQ-Bench Creative Writing | 1627 | — |
| WildBench | 85.7% | — |
| LiveBench Language | — | 50.7% |
Frequently asked questions
Is GPT-5 better than o3-mini?
GPT-5 is the stronger model overall, scoring 50.9 to 36.7 on the Noometry Index. o3-mini costs 1.8× less per token, which makes it the better buy when GPT-5's lead doesn't matter for your workload.
Which is cheaper, GPT-5 or o3-mini?
o3-mini is cheaper. It lists at $1.10 per million input tokens and $4.40 per million output tokens; GPT-5 lists at $1.25 and $10.
Is GPT-5 or o3-mini better for coding?
GPT-5 scores higher on coding benchmarks: 50.3 versus 40.8 in the Noometry coding category.
Which has the bigger context window?
GPT-5 does, with 400K tokens against 200K.
How many benchmarks do GPT-5 and o3-mini share?
42 benchmarks have published results for both models. GPT-5 has 69 scored results on Noometry and o3-mini has 51.