# Palm 2 vs Step 3

> Step 3 is the stronger model overall, scoring 40.5 to 30.0 on the Noometry Index.

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

## Summary

- They share 10 benchmarks with published results for both. Palm 2 scores higher in 0 categories and Step 3 in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Step 3 leads 54.3 to 25.6.
- Step 3 has downloadable open weights; the other is API-only.

## Snapshot

| | Palm 2 | Step 3 |
|---|---|---|
| Provider | Google | StepFun |
| Noometry Index | 30.0 | 40.5 |
| Rank | 298 | 149 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Proprietary | Open |

## Coding

- Palm 2: 29.0 (#311)
- Step 3: 40.1 (#147)

| Benchmark | Palm 2 | Step 3 |
|---|---|---|
| LMArena Coding | 994 | 1367 |

## Reasoning

- Palm 2: 19.1 (#271)
- Step 3: 28.4 (#105)

| Benchmark | Palm 2 | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1005 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |

## Math

- Palm 2: 30.8 (#231)
- Step 3: 37.6 (#148)

| Benchmark | Palm 2 | Step 3 |
|---|---|---|
| LMArena Math | 1049 | 1366 |

## Knowledge

- Palm 2: —
- Step 3: 36.8 (#164)

| Benchmark | Palm 2 | Step 3 |
|---|---|---|
| LMArena Expert | — | 1333 |

## Multimodal

- Palm 2: —
- Step 3: 35.5 (#86)

| Benchmark | Palm 2 | Step 3 |
|---|---|---|
| LMArena Vision | — | 1177 |

## Multilingual

- Palm 2: 20.9 (#295)
- Step 3: 46.3 (#159)

| Benchmark | Palm 2 | Step 3 |
|---|---|---|
| LMArena Non-English | 916 | 1327 |
| LMArena Chinese | 887 | 1397 |
| LMArena German | — | 1371 |
| LMArena Korean | — | 1269 |
| LMArena Russian | — | 1331 |
| LMArena Spanish | — | 1371 |

## Instruction Following

- Palm 2: 51.0 (#296)
- Step 3: 70.4 (#164)

| Benchmark | Palm 2 | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1010 | 1332 |

## Long Context

- Palm 2: 30.8 (#285)
- Step 3: 40.3 (#157)

| Benchmark | Palm 2 | Step 3 |
|---|---|---|
| LMArena Longer Query | 1010 | 1326 |

## Writing & Preference

- Palm 2: 25.6 (#304)
- Step 3: 54.3 (#151)

| Benchmark | Palm 2 | Step 3 |
|---|---|---|
| LMArena Text | 1027 | 1350 |
| LMArena Creative Writing | 991 | 1321 |
| LMArena Multi-Turn | 994 | 1341 |

## FAQ

### Is Palm 2 better than Step 3?

Step 3 is the stronger model overall, scoring 40.5 to 30.0 on the Noometry Index.

### Is Palm 2 or Step 3 better for coding?

Step 3 scores higher on coding benchmarks: 40.1 versus 29.0 in the Noometry coding category.

### How many benchmarks do Palm 2 and Step 3 share?

10 benchmarks have published results for both models. Palm 2 has 10 scored results on Noometry and Step 3 has 17.