# Olmo 3.1 32b Think vs Step 3.5 Flash

> Step 3.5 Flash is the stronger model overall, scoring 41.7 to 37.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/olmo-3-1-32b-think-vs-step-3-5-flash
- Last updated: 2026-10-10
- Shared benchmarks: 15

## Summary

- They share 15 benchmarks with published results for both. Olmo 3.1 32b Think scores higher in 1 category and Step 3.5 Flash in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Step 3.5 Flash leads 59.0 to 46.4.

## Snapshot

| | Olmo 3.1 32b Think | Step 3.5 Flash |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | StepFun |
| Noometry Index | 37.3 | 41.7 |
| Rank | 191 | 116 |
| Context | — | 256K |
| Input $/M | — | $0.10 |
| Output $/M | — | $0.30 |
| Weights | Open | Open |

## Coding

- Olmo 3.1 32b Think: 37.1 (#186)
- Step 3.5 Flash: 41.7 (#106)

| Benchmark | Olmo 3.1 32b Think | Step 3.5 Flash |
|---|---|---|
| LMArena Coding | 1292 | 1436 |

## Reasoning

- Olmo 3.1 32b Think: 24.1 (#151)
- Step 3.5 Flash: 21.2 (#202)

| Benchmark | Olmo 3.1 32b Think | Step 3.5 Flash |
|---|---|---|
| LMArena Hard Prompts | 1272 | 1411 |
| NYT Connections (extended) | — | 28.4% |

## Math

- Olmo 3.1 32b Think: 33.6 (#170)
- Step 3.5 Flash: 40.6 (#77)

| Benchmark | Olmo 3.1 32b Think | Step 3.5 Flash |
|---|---|---|
| LMArena Math | 1305 | 1408 |
| MathArena Final-Answer Competitions | — | 66.8% |

## Knowledge

- Olmo 3.1 32b Think: 35.0 (#178)
- Step 3.5 Flash: 39.0 (#127)

| Benchmark | Olmo 3.1 32b Think | Step 3.5 Flash |
|---|---|---|
| LMArena Expert | 1294 | 1422 |

## Multilingual

- Olmo 3.1 32b Think: 38.3 (#226)
- Step 3.5 Flash: 50.7 (#115)

| Benchmark | Olmo 3.1 32b Think | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | 1210 | 1386 |
| LMArena Chinese | 1241 | 1448 |
| LMArena French | 1262 | 1421 |
| LMArena German | 1260 | 1404 |
| LMArena Russian | 1193 | 1385 |
| LMArena Spanish | 1288 | 1419 |
| LMArena Japanese | — | 1353 |
| LMArena Korean | — | 1350 |

## Instruction Following

- Olmo 3.1 32b Think: 65.8 (#213)
- Step 3.5 Flash: 73.3 (#119)

| Benchmark | Olmo 3.1 32b Think | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1246 | 1385 |

## Long Context

- Olmo 3.1 32b Think: 38.6 (#190)
- Step 3.5 Flash: 42.8 (#112)

| Benchmark | Olmo 3.1 32b Think | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | 1272 | 1402 |

## Writing & Preference

- Olmo 3.1 32b Think: 46.4 (#215)
- Step 3.5 Flash: 59.0 (#108)

| Benchmark | Olmo 3.1 32b Think | Step 3.5 Flash |
|---|---|---|
| LMArena Text | 1271 | 1403 |
| LMArena Creative Writing | 1226 | 1357 |
| LMArena Multi-Turn | 1252 | 1405 |

## FAQ

### Is Olmo 3.1 32b Think better than Step 3.5 Flash?

Step 3.5 Flash is the stronger model overall, scoring 41.7 to 37.3 on the Noometry Index.

### Is Olmo 3.1 32b Think or Step 3.5 Flash better for coding?

Step 3.5 Flash scores higher on coding benchmarks: 41.7 versus 37.1 in the Noometry coding category.

### How many benchmarks do Olmo 3.1 32b Think and Step 3.5 Flash share?

15 benchmarks have published results for both models. Olmo 3.1 32b Think has 15 scored results on Noometry and Step 3.5 Flash has 19.