Model comparison
Olmo 3.1 32b Think vs Step 3
Step 3 is the stronger model overall, scoring 40.5 to 37.9 on the Noometry Index.
Last verified . 14 shared benchmarks.
Allen Institute for AI (Ai2)
StepFunSummary
- They share 14 benchmarks with published results for both. Olmo 3.1 32b Think scores higher in 0 categories and Step 3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Step 3 leads 46.3 to 38.1.
Side by side
| Olmo 3.1 32b Think | Step 3 | |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | StepFun |
| Noometry Index | 37.9 | 40.5 |
| Released | — | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 15 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3 leads
Olmo 3.1 32b Think: 37.7 (#189), Step 3: 40.1 (#147)
| Benchmark | Olmo 3.1 32b Think | Step 3 |
|---|---|---|
| LMArena Coding | 1291 | 1367 |
Reasoning Step 3 leads
Olmo 3.1 32b Think: 25.2 (#150), Step 3: 28.4 (#105)
| Benchmark | Olmo 3.1 32b Think | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1272 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |
Math Step 3 leads
Olmo 3.1 32b Think: 36.3 (#168), Step 3: 37.6 (#148)
| Benchmark | Olmo 3.1 32b Think | Step 3 |
|---|---|---|
| LMArena Math | 1305 | 1366 |
Knowledge Step 3 leads
Olmo 3.1 32b Think: 35.7 (#181), Step 3: 36.8 (#164)
| Benchmark | Olmo 3.1 32b Think | Step 3 |
|---|---|---|
| LMArena Expert | 1295 | 1333 |
Multimodal Not comparable
Olmo 3.1 32b Think: —, Step 3: 35.5 (#86)
| Benchmark | Olmo 3.1 32b Think | Step 3 |
|---|---|---|
| LMArena Vision | — | 1177 |
Multilingual Step 3 leads
Olmo 3.1 32b Think: 38.1 (#231), Step 3: 46.3 (#159)
| Benchmark | Olmo 3.1 32b Think | Step 3 |
|---|---|---|
| LMArena Non-English | 1209 | 1327 |
| LMArena Chinese | 1242 | 1397 |
| LMArena German | 1262 | 1371 |
| LMArena Russian | 1193 | 1331 |
| LMArena Spanish | 1289 | 1371 |
| LMArena French | 1260 | — |
| LMArena Korean | — | 1269 |
Instruction Following Step 3 leads
Olmo 3.1 32b Think: 65.6 (#218), Step 3: 70.4 (#164)
| Benchmark | Olmo 3.1 32b Think | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1247 | 1332 |
Long Context Step 3 leads
Olmo 3.1 32b Think: 38.6 (#195), Step 3: 40.3 (#157)
| Benchmark | Olmo 3.1 32b Think | Step 3 |
|---|---|---|
| LMArena Longer Query | 1272 | 1326 |
Writing & Preference Step 3 leads
Olmo 3.1 32b Think: 46.2 (#220), Step 3: 54.3 (#151)
| Benchmark | Olmo 3.1 32b Think | Step 3 |
|---|---|---|
| LMArena Text | 1272 | 1350 |
| LMArena Creative Writing | 1226 | 1321 |
| LMArena Multi-Turn | 1252 | 1341 |
Frequently asked questions
Is Olmo 3.1 32b Think better than Step 3?
Step 3 is the stronger model overall, scoring 40.5 to 37.9 on the Noometry Index.
Is Olmo 3.1 32b Think or Step 3 better for coding?
Step 3 scores higher on coding benchmarks: 40.1 versus 37.7 in the Noometry coding category.
How many benchmarks do Olmo 3.1 32b Think and Step 3 share?
14 benchmarks have published results for both models. Olmo 3.1 32b Think has 15 scored results on Noometry and Step 3 has 17.