Model comparison
Olmo 3.1 32b Instruct vs Step 3
Step 3 is the stronger model overall, scoring 40.5 to 39.4 on the Noometry Index.
Last verified . 15 shared benchmarks.
Allen Institute for AI (Ai2)
StepFunSummary
- They share 15 benchmarks with published results for both. Olmo 3.1 32b Instruct scores higher in 0 categories and Step 3 in 8 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Step 3 leads 54.3 to 50.2.
Side by side
| Olmo 3.1 32b Instruct | Step 3 | |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | StepFun |
| Noometry Index | 39.4 | 40.5 |
| Released | — | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 16 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Olmo 3.1 32b Instruct: 39.5 (#157), Step 3: 40.1 (#147)
| Benchmark | Olmo 3.1 32b Instruct | Step 3 |
|---|---|---|
| LMArena Coding | 1347 | 1367 |
Reasoning Step 3 leads
Olmo 3.1 32b Instruct: 26.4 (#132), Step 3: 28.4 (#105)
| Benchmark | Olmo 3.1 32b Instruct | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1322 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |
Math Step 3 leads
Olmo 3.1 32b Instruct: 36.3 (#167), Step 3: 37.6 (#148)
| Benchmark | Olmo 3.1 32b Instruct | Step 3 |
|---|---|---|
| LMArena Math | 1305 | 1366 |
Knowledge Too close to call
Olmo 3.1 32b Instruct: 36.1 (#175), Step 3: 36.8 (#164)
| Benchmark | Olmo 3.1 32b Instruct | Step 3 |
|---|---|---|
| LMArena Expert | 1308 | 1333 |
Multimodal Not comparable
Olmo 3.1 32b Instruct: —, Step 3: 35.5 (#86)
| Benchmark | Olmo 3.1 32b Instruct | Step 3 |
|---|---|---|
| LMArena Vision | — | 1177 |
Multilingual Step 3 leads
Olmo 3.1 32b Instruct: 42.6 (#191), Step 3: 46.3 (#159)
| Benchmark | Olmo 3.1 32b Instruct | Step 3 |
|---|---|---|
| LMArena Non-English | 1275 | 1327 |
| LMArena Chinese | 1304 | 1397 |
| LMArena German | 1282 | 1371 |
| LMArena Korean | 1206 | 1269 |
| LMArena Russian | 1268 | 1331 |
| LMArena Spanish | 1336 | 1371 |
| LMArena French | 1328 | — |
Instruction Following Step 3 leads
Olmo 3.1 32b Instruct: 68.6 (#187), Step 3: 70.4 (#164)
| Benchmark | Olmo 3.1 32b Instruct | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1299 | 1332 |
Long Context Too close to call
Olmo 3.1 32b Instruct: 39.9 (#166), Step 3: 40.3 (#157)
| Benchmark | Olmo 3.1 32b Instruct | Step 3 |
|---|---|---|
| LMArena Longer Query | 1312 | 1326 |
Writing & Preference Step 3 leads
Olmo 3.1 32b Instruct: 50.2 (#185), Step 3: 54.3 (#151)
| Benchmark | Olmo 3.1 32b Instruct | Step 3 |
|---|---|---|
| LMArena Text | 1311 | 1350 |
| LMArena Creative Writing | 1264 | 1321 |
| LMArena Multi-Turn | 1309 | 1341 |
Frequently asked questions
Is Olmo 3.1 32b Instruct better than Step 3?
Step 3 is the stronger model overall, scoring 40.5 to 39.4 on the Noometry Index.
Is Olmo 3.1 32b Instruct or Step 3 better for coding?
They score almost the same on coding (39.5 vs 40.1); test both on your own repository before choosing.
How many benchmarks do Olmo 3.1 32b Instruct and Step 3 share?
15 benchmarks have published results for both models. Olmo 3.1 32b Instruct has 16 scored results on Noometry and Step 3 has 17.