# GPT-6 Luna vs Step 3.7 Flash

> GPT-6 Luna is the stronger model overall, scoring 45.1 to 36.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-6-luna-vs-step-3-7-flash
- Last updated: 2026-10-10
- Shared benchmarks: 1

## Summary

- They share 1 benchmark with published results for both. GPT-6 Luna scores higher in 2 categories and Step 3.7 Flash in 1 category; 3 gaps are clear of the uncertainty.
- The widest gap is in coding, where GPT-6 Luna leads 54.7 to 39.4.
- The biggest single-benchmark swing is NYT Connections (extended): 68.7% for GPT-6 Luna and 39.7% for Step 3.7 Flash.
- GPT-6 Luna is cheaper at $0.10 / $0.50 per million input/output tokens, against $0.18 / $1.11 for Step 3.7 Flash.
- GPT-6 Luna accepts more context: 1.05M tokens versus 256K.
- Step 3.7 Flash has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-6 Luna | Step 3.7 Flash |
|---|---|---|
| Provider | OpenAI | StepFun |
| Noometry Index | 45.1 | 36.5 |
| Rank | 65 | 207 |
| Context | 1.05M | 256K |
| Input $/M | $0.10 | $0.18 |
| Output $/M | $0.50 | $1.11 |
| Weights | Proprietary | Open |

## Coding

- GPT-6 Luna: 54.7 (#24)
- Step 3.7 Flash: 39.4 (#147)

| Benchmark | GPT-6 Luna | Step 3.7 Flash |
|---|---|---|
| DeepSWE | 66.6% | — |
| FrontierCode | 42.4% | — |
| LMArena WebDev | 1583 | — |
| SciCode | — | 40% |
| LMArena Coding | 1448 | — |
| ALE-Bench | — | 694.12 |

## Reasoning

- GPT-6 Luna: 31.7 (#68)
- Step 3.7 Flash: 20.9 (#211)

| Benchmark | GPT-6 Luna | Step 3.7 Flash |
|---|---|---|
| NYT Connections (extended) | 68.7% | 39.7% |
| CritPt | — | 2.3% |
| LMArena Hard Prompts | 1415 | — |

## Math

- GPT-6 Luna: 35.6 (#140)
- Step 3.7 Flash: 40.9 (#74)

| Benchmark | GPT-6 Luna | Step 3.7 Flash |
|---|---|---|
| MathArena Final-Answer Competitions | — | 68.5% |
| LMArena Math | 1396 | — |

## Knowledge

- GPT-6 Luna: 40.1 (#110)
- Step 3.7 Flash: —

| Benchmark | GPT-6 Luna | Step 3.7 Flash |
|---|---|---|
| LMArena Expert | 1458 | — |

## Multimodal

- GPT-6 Luna: 42.0 (#27)
- Step 3.7 Flash: —

| Benchmark | GPT-6 Luna | Step 3.7 Flash |
|---|---|---|
| Furniture Assembly | 44.2% | — |

## Multilingual

- GPT-6 Luna: 51.0 (#111)
- Step 3.7 Flash: —

| Benchmark | GPT-6 Luna | Step 3.7 Flash |
|---|---|---|
| LMArena Non-English | 1390 | — |
| LMArena Chinese | 1425 | — |
| LMArena Russian | 1392 | — |
| LMArena Spanish | 1416 | — |

## Instruction Following

- GPT-6 Luna: 74.7 (#85)
- Step 3.7 Flash: —

| Benchmark | GPT-6 Luna | Step 3.7 Flash |
|---|---|---|
| LMArena Instruction Following | 1414 | — |

## Long Context

- GPT-6 Luna: 43.3 (#95)
- Step 3.7 Flash: —

| Benchmark | GPT-6 Luna | Step 3.7 Flash |
|---|---|---|
| LMArena Longer Query | 1417 | — |

## Writing & Preference

- GPT-6 Luna: 58.4 (#115)
- Step 3.7 Flash: —

| Benchmark | GPT-6 Luna | Step 3.7 Flash |
|---|---|---|
| LMArena Text | 1392 | — |
| LMArena Creative Writing | 1357 | — |
| LMArena Multi-Turn | 1400 | — |

## FAQ

### Is GPT-6 Luna better than Step 3.7 Flash?

GPT-6 Luna is the stronger model overall, scoring 45.1 to 36.5 on the Noometry Index.

### Which is cheaper, GPT-6 Luna or Step 3.7 Flash?

GPT-6 Luna is cheaper. It lists at $0.10 per million input tokens and $0.50 per million output tokens; Step 3.7 Flash lists at $0.18 and $1.11.

### Is GPT-6 Luna or Step 3.7 Flash better for coding?

GPT-6 Luna scores higher on coding benchmarks: 54.7 versus 39.4 in the Noometry coding category.

### Which has the bigger context window?

GPT-6 Luna does, with 1.05M tokens against 256K.

### How many benchmarks do GPT-6 Luna and Step 3.7 Flash share?

1 benchmark has published results for both models. GPT-6 Luna has 18 scored results on Noometry and Step 3.7 Flash has 5.