Model comparison
GPT-5 vs o1
GPT-5 is the stronger model overall, scoring 50.9 to 40.9 on the Noometry Index.
Last verified . 40 shared benchmarks.
Summary
- They share 40 benchmarks with published results for both. GPT-5 scores higher in 9 categories and o1 in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in long context, where GPT-5 leads 69.5 to 50.3.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 55.4% for GPT-5 and 14.7% for o1.
- GPT-5 is cheaper at $1.25 / $10 per million input/output tokens, against $15 / $60 for o1.
- GPT-5 accepts more context: 400K tokens versus 200K.
Side by side
| GPT-5 | o1 | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 50.9 | 40.9 |
| Released | 2025-08-07 | 2024-09-12 |
| Weights | Proprietary | Proprietary |
| Context window | 400K | 200K |
| Max output | 128K | 100K |
| Input $ / M tokens | $1.25 | $15 |
| Output $ / M tokens | $10 | $60 |
| Results tracked | 69 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5 leads
GPT-5: 50.3 (#47), o1: 46.1 (#70)
| Benchmark | GPT-5 | o1 |
|---|---|---|
| Aider Polyglot | 88% | 61.7% |
| WeirdML | 60.7% | 47.6% |
| LMArena Coding | 1436 | 1367 |
| SWE-bench Verified | 73.6% | — |
| SWE-bench Verified (bash only) | 65% | — |
| LMArena WebDev | 1418 | — |
| SciCode | 42.9% | — |
| GSO | 6.9% | — |
| LiveBench Coding | — | 69.7% |
| CadEval | — | 56% |
| ALE-Bench | 1,162 | — |
| AlgoTune | 1.67 | — |
| HumanEval+ | — | 89% |
| MBPP+ | — | 80.2% |
Agentic & Tool Use GPT-5 leads
GPT-5: 33.1 (#56), o1: 24.6 (#117)
| Benchmark | GPT-5 | o1 |
|---|---|---|
| METR Time Horizons | 69.6% | 51.1% |
| Terminal-Bench | 49.6% | — |
| GDPval | 34.8% | — |
| Remote Labor Index | 1.7% | — |
| Cybench | — | 10% |
| DeepResearch Bench | 49.6% | — |
| BALROG | 32.8% | — |
| LMArena Search | 1133 | — |
Reasoning GPT-5 leads
GPT-5: 38.3 (#64), o1: 27.9 (#111)
| Benchmark | GPT-5 | o1 |
|---|---|---|
| SimpleBench | 56.7% | 41.7% |
| ARC-AGI-1 | 65.7% | 30.7% |
| Chess Puzzles | 37% | 15% |
| EnigmaEval | 10.5% | 5.7% |
| LMArena Hard Prompts | 1416 | 1371 |
| DTBench | 90.7% | 74.7% |
| LMCA | 40% | 22.3% |
| Epoch Capabilities Index | 150 | 141.91 |
| ARC-AGI-2 | 9.9% | — |
| Kagi LLM Benchmark | 72.7% | — |
| CritPt | 12.6% | — |
| EBR-Bench | 12.7% | — |
| LiveBench Reasoning | — | 91.6% |
| Mystery Game Puzzles | 23% | — |
| LiveBench Data Analysis | — | 65.5% |
| ForecastBench | 61.4 | — |
| LiveBench | — | 75.7% |
Math GPT-5 leads
GPT-5: 55.0 (#44), o1: 36.1 (#175)
| Benchmark | GPT-5 | o1 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 55.4% | 14.7% |
| OTIS Mock AIME 2024-2025 | 91.4% | 73.3% |
| LMArena Math | 1407 | 1388 |
| MATH Level 5 | 98.1% | 94.7% |
| FrontierMath (Feb 2025 set) | 32.4% | 9.3% |
| FrontierMath Tier 4 | 22% | — |
| ProofBench | 18% | — |
| Omni-MATH | 64.7% | — |
| LiveBench Math | — | 80.3% |
| FrontierMath Tier 4 (v1) | 12.5% | — |
Knowledge GPT-5 leads
GPT-5: 56.6 (#43), o1: 41.5 (#110)
| Benchmark | GPT-5 | o1 |
|---|---|---|
| GPQA Diamond | 86.2% | 76.8% |
| Humanity's Last Exam | 25.3% | 8% |
| SimpleQA Verified | 50.1% | 41.1% |
| Confabulations | 10.3% | 11.7% |
| LMArena Expert | 1419 | 1361 |
| MMLU-Pro | 86.3% | — |
| Vectara Hallucination Rate | 14.7% | — |
| GPQA (HELM) | 79.2% | — |
Multimodal GPT-5 leads
GPT-5: 46.8 (#13), o1: 34.2 (#93)
| Benchmark | GPT-5 | o1 |
|---|---|---|
| LMArena Vision | 1232 | 1168 |
| GeoBench | 81% | 80% |
| VPCT | 66% | 37% |
| SpatialViz-Bench | — | 41.4% |
Multilingual GPT-5 leads
GPT-5: 51.4 (#110), o1: 48.6 (#142)
| Benchmark | GPT-5 | o1 |
|---|---|---|
| LMArena Non-English | 1397 | 1358 |
| LMArena Chinese | 1422 | 1394 |
| LMArena French | 1410 | 1344 |
| LMArena German | 1416 | 1337 |
| LMArena Japanese | 1409 | 1346 |
| LMArena Korean | 1360 | 1396 |
| LMArena Russian | 1406 | 1356 |
| LMArena Spanish | 1399 | 1345 |
Instruction Following Too close to call
GPT-5: 73.8 (#113), o1: 74.8 (#86)
| Benchmark | GPT-5 | o1 |
|---|---|---|
| LMArena Instruction Following | 1388 | 1367 |
| LiveBench Instruction Following | — | 81.5% |
| IFEval | 87.5% | — |
Long Context GPT-5 leads
GPT-5: 69.5 (#2), o1: 50.3 (#9)
| Benchmark | GPT-5 | o1 |
|---|---|---|
| Fiction.LiveBench | 97.2% | 83.3% |
| LMArena Longer Query | 1399 | 1378 |
Writing & Preference GPT-5 leads
GPT-5: 63.4 (#65), o1: 55.6 (#144)
| Benchmark | GPT-5 | o1 |
|---|---|---|
| LMArena Text | 1406 | 1366 |
| LMArena Creative Writing | 1365 | 1348 |
| Short-Story Creative Writing | 86% | 70.2% |
| LMArena Multi-Turn | 1426 | 1369 |
| EQ-Bench Creative Writing | 1627 | — |
| WildBench | 85.7% | — |
| LiveBench Language | — | 65.4% |
Frequently asked questions
Is GPT-5 better than o1?
GPT-5 is the stronger model overall, scoring 50.9 to 40.9 on the Noometry Index.
Which is cheaper, GPT-5 or o1?
GPT-5 is cheaper. It lists at $1.25 per million input tokens and $10 per million output tokens; o1 lists at $15 and $60.
Is GPT-5 or o1 better for coding?
GPT-5 scores higher on coding benchmarks: 50.3 versus 46.1 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 o1 share?
40 benchmarks have published results for both models. GPT-5 has 69 scored results on Noometry and o1 has 52.