Model comparison
Olmo 2 0325 32b Instruct vs Step 3.5 Flash
Step 3.5 Flash is the stronger model overall, scoring 42.3 to 32.7 on the Noometry Index.
Last verified . 11 shared benchmarks.
Allen Institute for AI (Ai2)
StepFunSummary
- They share 11 benchmarks with published results for both. Olmo 2 0325 32b Instruct scores higher in 1 category and Step 3.5 Flash in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Step 3.5 Flash leads 39.6 to 19.5.
Side by side
| Olmo 2 0325 32b Instruct | Step 3.5 Flash | |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | StepFun |
| Noometry Index | 32.7 | 42.3 |
| Released | — | 2026-01-29 |
| Weights | Open | Open |
| Context window | — | 256K |
| Max output | — | 256K |
| Input $ / M tokens | — | $0.10 |
| Output $ / M tokens | — | $0.30 |
| Results tracked | 16 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3.5 Flash leads
Olmo 2 0325 32b Instruct: 35.2 (#227), Step 3.5 Flash: 42.4 (#105)
| Benchmark | Olmo 2 0325 32b Instruct | Step 3.5 Flash |
|---|---|---|
| LMArena Coding | 1210 | 1436 |
Reasoning Olmo 2 0325 32b Instruct leads
Olmo 2 0325 32b Instruct: 23.6 (#175), Step 3.5 Flash: 22.2 (#202)
| Benchmark | Olmo 2 0325 32b Instruct | Step 3.5 Flash |
|---|---|---|
| LMArena Hard Prompts | 1208 | 1411 |
| NYT Connections (extended) | — | 28.4% |
Math Step 3.5 Flash leads
Olmo 2 0325 32b Instruct: 26.8 (#255), Step 3.5 Flash: 42.6 (#84)
| Benchmark | Olmo 2 0325 32b Instruct | Step 3.5 Flash |
|---|---|---|
| LMArena Math | 1208 | 1408 |
| MathArena Final-Answer Competitions | — | 66.8% |
| Omni-MATH | 16.1% | — |
Knowledge Step 3.5 Flash leads
Olmo 2 0325 32b Instruct: 19.5 (#279), Step 3.5 Flash: 39.6 (#132)
| Benchmark | Olmo 2 0325 32b Instruct | Step 3.5 Flash |
|---|---|---|
| MMLU-Pro | 41.4% | — |
| GPQA (HELM) | 28.7% | — |
| LMArena Expert | — | 1421 |
Multilingual Step 3.5 Flash leads
Olmo 2 0325 32b Instruct: 34.8 (#248), Step 3.5 Flash: 50.5 (#119)
| Benchmark | Olmo 2 0325 32b Instruct | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | 1160 | 1385 |
| LMArena Chinese | 1192 | 1447 |
| LMArena Russian | 1187 | 1385 |
| LMArena French | — | 1421 |
| LMArena German | — | 1405 |
| LMArena Japanese | — | 1354 |
| LMArena Korean | — | 1352 |
| LMArena Spanish | — | 1419 |
Instruction Following Step 3.5 Flash leads
Olmo 2 0325 32b Instruct: 61.5 (#244), Step 3.5 Flash: 73.1 (#124)
| Benchmark | Olmo 2 0325 32b Instruct | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1186 | 1385 |
| IFEval | 78% | — |
Long Context Step 3.5 Flash leads
Olmo 2 0325 32b Instruct: 36.2 (#234), Step 3.5 Flash: 42.8 (#117)
| Benchmark | Olmo 2 0325 32b Instruct | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | 1194 | 1402 |
Writing & Preference Step 3.5 Flash leads
Olmo 2 0325 32b Instruct: 42.1 (#236), Step 3.5 Flash: 58.8 (#113)
| Benchmark | Olmo 2 0325 32b Instruct | Step 3.5 Flash |
|---|---|---|
| LMArena Text | 1218 | 1403 |
| LMArena Creative Writing | 1199 | 1357 |
| LMArena Multi-Turn | 1221 | 1405 |
| WildBench | 73.4% | — |
Frequently asked questions
Is Olmo 2 0325 32b Instruct better than Step 3.5 Flash?
Step 3.5 Flash is the stronger model overall, scoring 42.3 to 32.7 on the Noometry Index.
Is Olmo 2 0325 32b Instruct or Step 3.5 Flash better for coding?
Step 3.5 Flash scores higher on coding benchmarks: 42.4 versus 35.2 in the Noometry coding category.
How many benchmarks do Olmo 2 0325 32b Instruct and Step 3.5 Flash share?
11 benchmarks have published results for both models. Olmo 2 0325 32b Instruct has 16 scored results on Noometry and Step 3.5 Flash has 19.