# GPT-6 Luna vs Step 5 Preview

> GPT-6 Luna is the stronger model overall, scoring 45.1 to 43.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-6-luna-vs-step-5-preview
- Last updated: 2026-10-10
- Shared benchmarks: 1

## Summary

- They share 1 benchmark with published results for both. GPT-6 Luna scores higher in 1 category and Step 5 Preview in 1 category; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Step 5 Preview leads 38.0 to 31.7.
- GPT-6 Luna is cheaper at $0.10 / $0.50 per million input/output tokens, against $1 / $2.70 for Step 5 Preview.
- GPT-6 Luna accepts more context: 1.05M tokens versus 1.02M.

## Snapshot

| | GPT-6 Luna | Step 5 Preview |
|---|---|---|
| Provider | OpenAI | StepFun |
| Noometry Index | 45.1 | 43.8 |
| Rank | 65 | 78 |
| Context | 1.05M | 1.02M |
| Input $/M | $0.10 | $1 |
| Output $/M | $0.50 | $2.70 |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-6 Luna: 54.7 (#24)
- Step 5 Preview: 50.6 (#40)

| Benchmark | GPT-6 Luna | Step 5 Preview |
|---|---|---|
| LMArena WebDev | 1583 | 1569 |
| DeepSWE | 66.6% | — |
| FrontierCode | 42.4% | — |
| SciCode | — | 58.9% |
| LMArena Coding | 1448 | — |

## Reasoning

- GPT-6 Luna: 31.7 (#68)
- Step 5 Preview: 38.0 (#58)

| Benchmark | GPT-6 Luna | Step 5 Preview |
|---|---|---|
| NYT Connections (extended) | 68.7% | — |
| CritPt | — | 20.9% |
| LMArena Hard Prompts | 1415 | — |

## Math

- GPT-6 Luna: 35.6 (#140)
- Step 5 Preview: —

| Benchmark | GPT-6 Luna | Step 5 Preview |
|---|---|---|
| LMArena Math | 1396 | — |

## Knowledge

- GPT-6 Luna: 40.1 (#110)
- Step 5 Preview: —

| Benchmark | GPT-6 Luna | Step 5 Preview |
|---|---|---|
| LMArena Expert | 1458 | — |

## Multimodal

- GPT-6 Luna: 42.0 (#27)
- Step 5 Preview: —

| Benchmark | GPT-6 Luna | Step 5 Preview |
|---|---|---|
| Furniture Assembly | 44.2% | — |

## Multilingual

- GPT-6 Luna: 51.0 (#111)
- Step 5 Preview: —

| Benchmark | GPT-6 Luna | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1390 | — |
| LMArena Chinese | 1425 | — |
| LMArena Russian | 1392 | — |
| LMArena Spanish | 1416 | — |

## Instruction Following

- GPT-6 Luna: 74.7 (#85)
- Step 5 Preview: —

| Benchmark | GPT-6 Luna | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1414 | — |

## Long Context

- GPT-6 Luna: 43.3 (#95)
- Step 5 Preview: —

| Benchmark | GPT-6 Luna | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1417 | — |

## Writing & Preference

- GPT-6 Luna: 58.4 (#115)
- Step 5 Preview: —

| Benchmark | GPT-6 Luna | Step 5 Preview |
|---|---|---|
| LMArena Text | 1392 | — |
| LMArena Creative Writing | 1357 | — |
| LMArena Multi-Turn | 1400 | — |

## FAQ

### Is GPT-6 Luna better than Step 5 Preview?

GPT-6 Luna is the stronger model overall, scoring 45.1 to 43.8 on the Noometry Index.

### Which is cheaper, GPT-6 Luna or Step 5 Preview?

GPT-6 Luna is cheaper. It lists at $0.10 per million input tokens and $0.50 per million output tokens; Step 5 Preview lists at $1 and $2.70.

### Is GPT-6 Luna or Step 5 Preview better for coding?

GPT-6 Luna scores higher on coding benchmarks: 54.7 versus 50.6 in the Noometry coding category.

### Which has the bigger context window?

GPT-6 Luna does, with 1.05M tokens against 1.02M.

### How many benchmarks do GPT-6 Luna and Step 5 Preview share?

1 benchmark has published results for both models. GPT-6 Luna has 18 scored results on Noometry and Step 5 Preview has 3.