Model comparison
Palm 2 vs Step 3
Step 3 is the stronger model overall, scoring 40.5 to 30.0 on the Noometry Index.
Last verified . 10 shared benchmarks.
Google
StepFunSummary
- 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.
Side by side
| Palm 2 | Step 3 | |
|---|---|---|
| Provider | StepFun | |
| Noometry Index | 30.0 | 40.5 |
| Released | — | — |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 10 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3 leads
Palm 2: 29.0 (#311), Step 3: 40.1 (#147)
| Benchmark | Palm 2 | Step 3 |
|---|---|---|
| LMArena Coding | 994 | 1367 |
Reasoning Step 3 leads
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 Step 3 leads
Palm 2: 30.8 (#231), Step 3: 37.6 (#148)
| Benchmark | Palm 2 | Step 3 |
|---|---|---|
| LMArena Math | 1049 | 1366 |
Knowledge Not comparable
Palm 2: —, Step 3: 36.8 (#164)
| Benchmark | Palm 2 | Step 3 |
|---|---|---|
| LMArena Expert | — | 1333 |
Multimodal Not comparable
Palm 2: —, Step 3: 35.5 (#86)
| Benchmark | Palm 2 | Step 3 |
|---|---|---|
| LMArena Vision | — | 1177 |
Multilingual Step 3 leads
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 Step 3 leads
Palm 2: 51.0 (#296), Step 3: 70.4 (#164)
| Benchmark | Palm 2 | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1010 | 1332 |
Long Context Step 3 leads
Palm 2: 30.8 (#285), Step 3: 40.3 (#157)
| Benchmark | Palm 2 | Step 3 |
|---|---|---|
| LMArena Longer Query | 1010 | 1326 |
Writing & Preference Step 3 leads
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 |
Frequently asked questions
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.