# Olmo 3 32b Think vs Step 3

> Step 3 is the stronger model overall, scoring 40.5 to 38.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/olmo-3-32b-think-vs-step-3
- Last updated: 2026-10-10
- Shared benchmarks: 13

## Summary

- They share 13 benchmarks with published results for both. Olmo 3 32b Think scores higher in 0 categories and Step 3 in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Step 3 leads 54.3 to 49.1.

## Snapshot

| | Olmo 3 32b Think | Step 3 |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | StepFun |
| Noometry Index | 38.7 | 40.5 |
| Rank | 183 | 149 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Olmo 3 32b Think: 38.6 (#172)
- Step 3: 40.1 (#147)

| Benchmark | Olmo 3 32b Think | Step 3 |
|---|---|---|
| LMArena Coding | 1319 | 1367 |

## Reasoning

- Olmo 3 32b Think: 25.9 (#140)
- Step 3: 28.4 (#105)

| Benchmark | Olmo 3 32b Think | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1302 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |

## Math

- Olmo 3 32b Think: 36.5 (#165)
- Step 3: 37.6 (#148)

| Benchmark | Olmo 3 32b Think | Step 3 |
|---|---|---|
| LMArena Math | 1316 | 1366 |

## Knowledge

- Olmo 3 32b Think: 35.0 (#190)
- Step 3: 36.8 (#164)

| Benchmark | Olmo 3 32b Think | Step 3 |
|---|---|---|
| LMArena Expert | 1273 | 1333 |

## Multimodal

- Olmo 3 32b Think: —
- Step 3: 35.5 (#86)

| Benchmark | Olmo 3 32b Think | Step 3 |
|---|---|---|
| LMArena Vision | — | 1177 |

## Multilingual

- Olmo 3 32b Think: 41.2 (#210)
- Step 3: 46.3 (#159)

| Benchmark | Olmo 3 32b Think | Step 3 |
|---|---|---|
| LMArena Non-English | 1255 | 1327 |
| LMArena Chinese | 1300 | 1397 |
| LMArena German | 1290 | 1371 |
| LMArena Russian | 1254 | 1331 |
| LMArena French | 1291 | — |
| LMArena Korean | — | 1269 |
| LMArena Spanish | — | 1371 |

## Instruction Following

- Olmo 3 32b Think: 67.2 (#198)
- Step 3: 70.4 (#164)

| Benchmark | Olmo 3 32b Think | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1275 | 1332 |

## Long Context

- Olmo 3 32b Think: 39.4 (#182)
- Step 3: 40.3 (#157)

| Benchmark | Olmo 3 32b Think | Step 3 |
|---|---|---|
| LMArena Longer Query | 1296 | 1326 |

## Writing & Preference

- Olmo 3 32b Think: 49.1 (#193)
- Step 3: 54.3 (#151)

| Benchmark | Olmo 3 32b Think | Step 3 |
|---|---|---|
| LMArena Text | 1300 | 1350 |
| LMArena Creative Writing | 1256 | 1321 |
| LMArena Multi-Turn | 1290 | 1341 |

## FAQ

### Is Olmo 3 32b Think better than Step 3?

Step 3 is the stronger model overall, scoring 40.5 to 38.7 on the Noometry Index.

### Is Olmo 3 32b Think or Step 3 better for coding?

Step 3 scores higher on coding benchmarks: 40.1 versus 38.6 in the Noometry coding category.

### How many benchmarks do Olmo 3 32b Think and Step 3 share?

13 benchmarks have published results for both models. Olmo 3 32b Think has 14 scored results on Noometry and Step 3 has 17.