# o1 vs Step 5 Preview

> Step 5 Preview is the stronger model overall, scoring 47.9 to 40.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/o1-vs-step-5-preview
- Last updated: 2026-10-10
- Shared benchmarks: 14

## Summary

- They share 14 benchmarks with published results for both. o1 scores higher in 2 categories and Step 5 Preview in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Step 5 Preview leads 40.0 to 27.9.
- Step 5 Preview is cheaper at $1 / $2.70 per million input/output tokens, against $15 / $60 for o1.
- Step 5 Preview accepts more context: 1.02M tokens versus 200K.

## Snapshot

| | o1 | Step 5 Preview |
|---|---|---|
| Provider | OpenAI | StepFun |
| Noometry Index | 40.9 | 47.9 |
| Rank | 143 | 58 |
| Context | 200K | 1.02M |
| Input $/M | $15 | $1 |
| Output $/M | $60 | $2.70 |
| Weights | Proprietary | Proprietary |

## Coding

- o1: 46.1 (#70)
- Step 5 Preview: 51.8 (#36)

| Benchmark | o1 | Step 5 Preview |
|---|---|---|
| LMArena Coding | 1367 | 1480 |
| Aider Polyglot | 61.7% | — |
| LMArena WebDev | — | 1564 |
| SciCode | — | 58.9% |
| WeirdML | 47.6% | — |
| LiveBench Coding | 69.7% | — |
| CadEval | 56% | — |
| HumanEval+ | 89% | — |
| MBPP+ | 80.2% | — |

## Agentic & Tool Use

- o1: 24.6 (#117)
- Step 5 Preview: —

| Benchmark | o1 | Step 5 Preview |
|---|---|---|
| Cybench | 10% | — |
| METR Time Horizons | 51.1% | — |

## Reasoning

- o1: 27.9 (#111)
- Step 5 Preview: 40.0 (#57)

| Benchmark | o1 | Step 5 Preview |
|---|---|---|
| LMArena Hard Prompts | 1371 | 1465 |
| SimpleBench | 41.7% | — |
| ARC-AGI-1 | 30.7% | — |
| CritPt | — | 20.9% |
| Chess Puzzles | 15% | — |
| EnigmaEval | 5.7% | — |
| LiveBench Reasoning | 91.6% | — |
| DTBench | 74.7% | — |
| LiveBench Data Analysis | 65.5% | — |
| LMCA | 22.3% | — |
| Epoch Capabilities Index | 141.91 | — |
| LiveBench | 75.7% | — |

## Math

- o1: 36.1 (#175)
- Step 5 Preview: 46.1 (#72)

| Benchmark | o1 | Step 5 Preview |
|---|---|---|
| LMArena Math | 1388 | 1470 |
| FrontierMath (Tiers 1-3) | 14.7% | — |
| OTIS Mock AIME 2024-2025 | 73.3% | — |
| ProofBench | — | 42% |
| LiveBench Math | 80.3% | — |
| MATH Level 5 | 94.7% | — |
| FrontierMath (Feb 2025 set) | 9.3% | — |

## Knowledge

- o1: 41.5 (#110)
- Step 5 Preview: 41.2 (#112)

| Benchmark | o1 | Step 5 Preview |
|---|---|---|
| LMArena Expert | 1361 | 1470 |
| GPQA Diamond | 76.8% | — |
| Humanity's Last Exam | 8% | — |
| SimpleQA Verified | 41.1% | — |
| Confabulations | 11.7% | — |

## Multimodal

- o1: 34.2 (#93)
- Step 5 Preview: 41.0 (#41)

| Benchmark | o1 | Step 5 Preview |
|---|---|---|
| LMArena Vision | 1168 | 1267 |
| GeoBench | 80% | — |
| VPCT | 37% | — |
| SpatialViz-Bench | 41.4% | — |

## Multilingual

- o1: 48.6 (#142)
- Step 5 Preview: 53.8 (#54)

| Benchmark | o1 | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1358 | 1432 |
| LMArena Chinese | 1394 | 1519 |
| LMArena Russian | 1356 | 1436 |
| LMArena Spanish | 1345 | 1439 |
| LMArena French | 1344 | — |
| LMArena German | 1337 | — |
| LMArena Japanese | 1346 | — |
| LMArena Korean | 1396 | — |

## Instruction Following

- o1: 74.8 (#86)
- Step 5 Preview: 76.0 (#50)

| Benchmark | o1 | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1367 | 1444 |
| LiveBench Instruction Following | 81.5% | — |

## Long Context

- o1: 50.3 (#9)
- Step 5 Preview: 44.5 (#64)

| Benchmark | o1 | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1378 | 1455 |
| Fiction.LiveBench | 83.3% | — |

## Writing & Preference

- o1: 55.6 (#144)
- Step 5 Preview: 62.8 (#71)

| Benchmark | o1 | Step 5 Preview |
|---|---|---|
| LMArena Text | 1366 | 1442 |
| LMArena Creative Writing | 1348 | 1410 |
| LMArena Multi-Turn | 1369 | 1447 |
| Short-Story Creative Writing | 70.2% | — |
| LiveBench Language | 65.4% | — |

## FAQ

### Is o1 better than Step 5 Preview?

Step 5 Preview is the stronger model overall, scoring 47.9 to 40.9 on the Noometry Index.

### Which is cheaper, o1 or Step 5 Preview?

Step 5 Preview is cheaper. It lists at $1 per million input tokens and $2.70 per million output tokens; o1 lists at $15 and $60.

### Is o1 or Step 5 Preview better for coding?

Step 5 Preview scores higher on coding benchmarks: 51.8 versus 46.1 in the Noometry coding category.

### Which has the bigger context window?

Step 5 Preview does, with 1.02M tokens against 200K.

### How many benchmarks do o1 and Step 5 Preview share?

14 benchmarks have published results for both models. o1 has 52 scored results on Noometry and Step 5 Preview has 18.