# Molmo 2 8b vs Step 3

> Step 3 is the stronger model overall, scoring 39.9 to 38.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/molmo-2-8b-vs-step-3
- Last updated: 2026-10-10
- Shared benchmarks: 5

## Summary

- They share 5 benchmarks with published results for both. Molmo 2 8b scores higher in 0 categories and Step 3 in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in multimodal, where Step 3 leads 34.9 to 29.5.

## Snapshot

| | Molmo 2 8b | Step 3 |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | StepFun |
| Noometry Index | 38.7 | 39.9 |
| Rank | 170 | 145 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Molmo 2 8b: —
- Step 3: 39.5 (#144)

| Benchmark | Molmo 2 8b | Step 3 |
|---|---|---|
| LMArena Coding | — | 1367 |

## Reasoning

- Molmo 2 8b: 24.5 (#146)
- Step 3: 27.6 (#102)

| Benchmark | Molmo 2 8b | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1288 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |

## Math

- Molmo 2 8b: —
- Step 3: 34.9 (#148)

| Benchmark | Molmo 2 8b | Step 3 |
|---|---|---|
| LMArena Math | — | 1366 |

## Knowledge

- Molmo 2 8b: —
- Step 3: 36.2 (#161)

| Benchmark | Molmo 2 8b | Step 3 |
|---|---|---|
| LMArena Expert | — | 1333 |

## Multimodal

- Molmo 2 8b: 29.5 (#106)
- Step 3: 34.9 (#81)

| Benchmark | Molmo 2 8b | Step 3 |
|---|---|---|
| LMArena Vision | 1081 | 1176 |

## Multilingual

- Molmo 2 8b: 42.8 (#186)
- Step 3: 46.5 (#154)

| Benchmark | Molmo 2 8b | Step 3 |
|---|---|---|
| LMArena Non-English | 1275 | 1327 |
| LMArena Chinese | — | 1396 |
| LMArena German | — | 1371 |
| LMArena Korean | — | 1271 |
| LMArena Russian | — | 1331 |
| LMArena Spanish | — | 1372 |

## Instruction Following

- Molmo 2 8b: 67.2 (#196)
- Step 3: 70.6 (#159)

| Benchmark | Molmo 2 8b | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1270 | 1332 |

## Long Context

- Molmo 2 8b: —
- Step 3: 40.3 (#152)

| Benchmark | Molmo 2 8b | Step 3 |
|---|---|---|
| LMArena Longer Query | — | 1326 |

## Writing & Preference

- Molmo 2 8b: 49.5 (#187)
- Step 3: 54.5 (#146)

| Benchmark | Molmo 2 8b | Step 3 |
|---|---|---|
| LMArena Text | 1288 | 1351 |
| LMArena Creative Writing | — | 1322 |
| LMArena Multi-Turn | — | 1340 |

## FAQ

### Is Molmo 2 8b better than Step 3?

Step 3 is the stronger model overall, scoring 39.9 to 38.7 on the Noometry Index.

### How many benchmarks do Molmo 2 8b and Step 3 share?

5 benchmarks have published results for both models. Molmo 2 8b has 5 scored results on Noometry and Step 3 has 17.