# GPT-5.5 vs o1

> GPT-5.5 is the stronger model overall, scoring 63.4 to 40.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-5-5-vs-o1
- Last updated: 2026-10-11
- Shared benchmarks: 30

## Summary

- They share 30 benchmarks with published results for both. GPT-5.5 scores higher in 9 categories and o1 in 1 category; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.5 leads 81.7 to 36.1.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 85.3% for GPT-5.5 and 14.7% for o1.
- GPT-5.5 is cheaper at $5 / $30 per million input/output tokens, against $15 / $60 for o1.
- GPT-5.5 accepts more context: 1.05M tokens versus 200K.

## Snapshot

| | GPT-5.5 | o1 |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 63.4 | 40.9 |
| Rank | 9 | 143 |
| Context | 1.05M | 200K |
| Input $/M | $5 | $15 |
| Output $/M | $30 | $60 |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-5.5: 58.2 (#17)
- o1: 46.1 (#70)

| Benchmark | GPT-5.5 | o1 |
|---|---|---|
| WeirdML | 84.9% | 47.6% |
| LMArena Coding | 1494 | 1367 |
| SWE-bench Verified | 80.6% | — |
| DeepSWE | 67% | — |
| FrontierCode | 43% | — |
| Aider Polyglot | — | 61.7% |
| LMArena WebDev | 1513 | — |
| SciCode | 56.1% | — |
| GSO | 40.2% | — |
| LiveBench Coding | — | 69.7% |
| MirrorCode | 10% | — |
| CadEval | — | 56% |
| ALE-Bench | 1,943 | — |
| HumanEval+ | — | 89% |
| MBPP+ | — | 80.2% |

## Agentic & Tool Use

- GPT-5.5: 50.7 (#6)
- o1: 24.6 (#117)

| Benchmark | GPT-5.5 | o1 |
|---|---|---|
| Terminal-Bench | 84.7% | — |
| APEX-Agents | 55.1% | — |
| OSWorld 2.0 | 13% | — |
| Remote Labor Index | 6.3% | — |
| τ²-bench Banking | 44.6% | — |
| Cybench | — | 10% |
| DeepResearch Bench | 54% | — |
| PostTrainBench | 27.2% | — |
| ExploitBench | 47.4% | — |
| GBAEval | 53.2% | — |
| GDP.pdf | 26% | — |
| LMArena Search | 1242 | — |
| METR Time Horizons | — | 51.1% |
| Vending-Bench 2 | 7,524 | — |

## Reasoning

- GPT-5.5: 72.8 (#11)
- o1: 27.9 (#111)

| Benchmark | GPT-5.5 | o1 |
|---|---|---|
| SimpleBench | 69% | 41.7% |
| ARC-AGI-1 | 95% | 30.7% |
| Chess Puzzles | 54% | 15% |
| LMArena Hard Prompts | 1489 | 1371 |
| DTBench | 96% | 74.7% |
| LMCA | 54.3% | 22.3% |
| Epoch Capabilities Index | 159.1 | 141.91 |
| ARC-AGI-2 | 85% | — |
| Kagi LLM Benchmark | 88.8% | — |
| NYT Connections (extended) | 96.2% | — |
| CritPt | 27.1% | — |
| EnigmaEval | — | 5.7% |
| EBR-Bench | 34.3% | — |
| LiveBench Reasoning | — | 91.6% |
| Mystery Game Puzzles | 56% | — |
| LiveBench Data Analysis | — | 65.5% |
| Surface Evolver Bench | 88.1% | — |
| Bench to the Future 3 | 0.14 | — |
| ForecastBench | 60.6 | — |
| LiveBench | — | 75.7% |

## Math

- GPT-5.5: 81.7 (#11)
- o1: 36.1 (#175)

| Benchmark | GPT-5.5 | o1 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 85.3% | 14.7% |
| OTIS Mock AIME 2024-2025 | 100% | 73.3% |
| LMArena Math | 1486 | 1388 |
| FrontierMath (Feb 2025 set) | 51.7% | 9.3% |
| FrontierMath Tier 4 | 72.5% | — |
| MathArena Final-Answer Competitions | 94.3% | — |
| ProofBench | 50% | — |
| LiveBench Math | — | 80.3% |
| MATH Level 5 | — | 94.7% |
| FrontierMath Erdős | 0% | — |
| FrontierMath Tier 4 (v1) | 35.4% | — |

## Knowledge

- GPT-5.5: 64.4 (#17)
- o1: 41.5 (#110)

| Benchmark | GPT-5.5 | o1 |
|---|---|---|
| GPQA Diamond | 94% | 76.8% |
| SimpleQA Verified | 63% | 41.1% |
| LMArena Expert | 1508 | 1361 |
| Humanity's Last Exam | — | 8% |
| Confabulations | — | 11.7% |
| Vectara Hallucination Rate | 9.3% | — |

## Multimodal

- GPT-5.5: 46.9 (#12)
- o1: 34.2 (#93)

| Benchmark | GPT-5.5 | o1 |
|---|---|---|
| LMArena Vision | 1297 | 1168 |
| GeoBench | — | 80% |
| VPCT | — | 37% |
| Blueprint-Bench 2 | 36.2% | — |
| Furniture Assembly | 44.2% | — |
| LMArena Document | 1486 | — |
| SpatialViz-Bench | — | 41.4% |

## Multilingual

- GPT-5.5: 56.4 (#20)
- o1: 48.6 (#142)

| Benchmark | GPT-5.5 | o1 |
|---|---|---|
| LMArena Non-English | 1467 | 1358 |
| LMArena Chinese | 1533 | 1394 |
| LMArena French | 1486 | 1344 |
| LMArena German | 1480 | 1337 |
| LMArena Japanese | 1498 | 1346 |
| LMArena Korean | 1460 | 1396 |
| LMArena Russian | 1473 | 1356 |
| LMArena Spanish | 1468 | 1345 |

## Instruction Following

- GPT-5.5: 77.5 (#18)
- o1: 74.8 (#86)

| Benchmark | GPT-5.5 | o1 |
|---|---|---|
| LMArena Instruction Following | 1479 | 1367 |
| LiveBench Instruction Following | — | 81.5% |

## Long Context

- GPT-5.5: 48.3 (#12)
- o1: 50.3 (#9)

| Benchmark | GPT-5.5 | o1 |
|---|---|---|
| LMArena Longer Query | 1484 | 1378 |
| Fiction.LiveBench | — | 83.3% |
| CL-bench Life | 22.2% | — |

## Writing & Preference

- GPT-5.5: 72.7 (#13)
- o1: 55.6 (#144)

| Benchmark | GPT-5.5 | o1 |
|---|---|---|
| LMArena Text | 1472 | 1366 |
| LMArena Creative Writing | 1455 | 1348 |
| LMArena Multi-Turn | 1476 | 1369 |
| Short-Story Creative Writing | — | 70.2% |
| EQ-Bench Creative Writing | 1844 | — |
| EQ-Bench 4 | 1315 | — |
| LiveBench Language | — | 65.4% |

## FAQ

### Is GPT-5.5 better than o1?

GPT-5.5 is the stronger model overall, scoring 63.4 to 40.9 on the Noometry Index.

### Which is cheaper, GPT-5.5 or o1?

GPT-5.5 is cheaper. It lists at $5 per million input tokens and $30 per million output tokens; o1 lists at $15 and $60.

### Is GPT-5.5 or o1 better for coding?

GPT-5.5 scores higher on coding benchmarks: 58.2 versus 46.1 in the Noometry coding category.

### Which has the bigger context window?

GPT-5.5 does, with 1.05M tokens against 200K.

### How many benchmarks do GPT-5.5 and o1 share?

30 benchmarks have published results for both models. GPT-5.5 has 71 scored results on Noometry and o1 has 52.