Model comparison
Olmo 3 32b Think vs Step 2 16k Exp 202412
Olmo 3 32b Think and Step 2 16k Exp 202412 score almost the same on the Noometry Index (38.7 vs 39.2), so choose on price, context window or the category you care about most.
Last verified . 12 shared benchmarks.
Allen Institute for AI (Ai2)
StepFunSummary
- They share 12 benchmarks with published results for both. Olmo 3 32b Think scores higher in 3 categories and Step 2 16k Exp 202412 in 5 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Step 2 16k Exp 202412 leads 52.3 to 49.1.
- Olmo 3 32b Think has downloadable open weights; the other is API-only.
Side by side
| Olmo 3 32b Think | Step 2 16k Exp 202412 | |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | StepFun |
| Noometry Index | 38.7 | 39.2 |
| Released | — | — |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 14 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Olmo 3 32b Think: 38.6 (#172), Step 2 16k Exp 202412: 38.5 (#174)
| Benchmark | Olmo 3 32b Think | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Coding | 1319 | 1316 |
Reasoning Too close to call
Olmo 3 32b Think: 25.9 (#140), Step 2 16k Exp 202412: 25.9 (#142)
| Benchmark | Olmo 3 32b Think | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Hard Prompts | 1302 | 1299 |
Math Too close to call
Olmo 3 32b Think: 36.5 (#165), Step 2 16k Exp 202412: 36.3 (#169)
| Benchmark | Olmo 3 32b Think | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Math | 1316 | 1304 |
Knowledge Too close to call
Olmo 3 32b Think: 35.0 (#190), Step 2 16k Exp 202412: 35.2 (#187)
| Benchmark | Olmo 3 32b Think | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Expert | 1273 | 1279 |
Multilingual Step 2 16k Exp 202412 leads
Olmo 3 32b Think: 41.2 (#210), Step 2 16k Exp 202412: 43.7 (#181)
| Benchmark | Olmo 3 32b Think | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Non-English | 1255 | 1290 |
| LMArena Chinese | 1300 | 1331 |
| LMArena Russian | 1254 | 1324 |
| LMArena French | 1291 | — |
| LMArena German | 1290 | — |
Instruction Following Too close to call
Olmo 3 32b Think: 67.2 (#198), Step 2 16k Exp 202412: 67.9 (#192)
| Benchmark | Olmo 3 32b Think | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Instruction Following | 1275 | 1287 |
Long Context Too close to call
Olmo 3 32b Think: 39.4 (#182), Step 2 16k Exp 202412: 39.7 (#170)
| Benchmark | Olmo 3 32b Think | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Longer Query | 1296 | 1307 |
Writing & Preference Step 2 16k Exp 202412 leads
Olmo 3 32b Think: 49.1 (#193), Step 2 16k Exp 202412: 52.3 (#173)
| Benchmark | Olmo 3 32b Think | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Text | 1300 | 1321 |
| LMArena Creative Writing | 1256 | 1328 |
| LMArena Multi-Turn | 1290 | 1292 |
Frequently asked questions
Is Olmo 3 32b Think better than Step 2 16k Exp 202412?
Olmo 3 32b Think and Step 2 16k Exp 202412 score almost the same on the Noometry Index (38.7 vs 39.2), so choose on price, context window or the category you care about most.
Is Olmo 3 32b Think or Step 2 16k Exp 202412 better for coding?
They score almost the same on coding (38.6 vs 38.5); test both on your own repository before choosing.
How many benchmarks do Olmo 3 32b Think and Step 2 16k Exp 202412 share?
12 benchmarks have published results for both models. Olmo 3 32b Think has 14 scored results on Noometry and Step 2 16k Exp 202412 has 12.