Model comparison
Molmo 2 8b vs Step 5 Preview
Step 5 Preview is the stronger model overall, scoring 47.9 to 39.1 on the Noometry Index.
Last verified . 5 shared benchmarks.
Allen Institute for AI (Ai2)
StepFunSummary
- They share 5 benchmarks with published results for both. Molmo 2 8b scores higher in 0 categories and Step 5 Preview in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Step 5 Preview leads 40.0 to 25.6.
- Molmo 2 8b has downloadable open weights; the other is API-only.
Side by side
| Molmo 2 8b | Step 5 Preview | |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | StepFun |
| Noometry Index | 39.1 | 47.9 |
| Released | — | 2026-09-16 |
| Weights | Open | Proprietary |
| Context window | — | 1.02M |
| Max output | — | 66K |
| Input $ / M tokens | — | $1 |
| Output $ / M tokens | — | $2.70 |
| Results tracked | 5 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Molmo 2 8b: —, Step 5 Preview: 51.8 (#36)
| Benchmark | Molmo 2 8b | Step 5 Preview |
|---|---|---|
| LMArena WebDev | — | 1564 |
| SciCode | — | 58.9% |
| LMArena Coding | — | 1480 |
Reasoning Step 5 Preview leads
Molmo 2 8b: 25.6 (#146), Step 5 Preview: 40.0 (#57)
| Benchmark | Molmo 2 8b | Step 5 Preview |
|---|---|---|
| LMArena Hard Prompts | 1287 | 1465 |
| CritPt | — | 20.9% |
Math Not comparable
Molmo 2 8b: —, Step 5 Preview: 46.1 (#72)
| Benchmark | Molmo 2 8b | Step 5 Preview |
|---|---|---|
| ProofBench | — | 42% |
| LMArena Math | — | 1470 |
Knowledge Not comparable
Molmo 2 8b: —, Step 5 Preview: 41.2 (#112)
| Benchmark | Molmo 2 8b | Step 5 Preview |
|---|---|---|
| LMArena Expert | — | 1470 |
Multimodal Step 5 Preview leads
Molmo 2 8b: 30.2 (#112), Step 5 Preview: 41.0 (#41)
| Benchmark | Molmo 2 8b | Step 5 Preview |
|---|---|---|
| LMArena Vision | 1081 | 1267 |
Multilingual Step 5 Preview leads
Molmo 2 8b: 42.7 (#190), Step 5 Preview: 53.8 (#54)
| Benchmark | Molmo 2 8b | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1276 | 1432 |
| LMArena Chinese | — | 1519 |
| LMArena Russian | — | 1436 |
| LMArena Spanish | — | 1439 |
Instruction Following Step 5 Preview leads
Molmo 2 8b: 67.0 (#201), Step 5 Preview: 76.0 (#50)
| Benchmark | Molmo 2 8b | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1270 | 1444 |
Long Context Not comparable
Molmo 2 8b: —, Step 5 Preview: 44.5 (#64)
| Benchmark | Molmo 2 8b | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | — | 1455 |
Writing & Preference Step 5 Preview leads
Molmo 2 8b: 49.4 (#191), Step 5 Preview: 62.8 (#71)
| Benchmark | Molmo 2 8b | Step 5 Preview |
|---|---|---|
| LMArena Text | 1288 | 1442 |
| LMArena Creative Writing | — | 1410 |
| LMArena Multi-Turn | — | 1447 |
Frequently asked questions
Is Molmo 2 8b better than Step 5 Preview?
Step 5 Preview is the stronger model overall, scoring 47.9 to 39.1 on the Noometry Index.
How many benchmarks do Molmo 2 8b and Step 5 Preview share?
5 benchmarks have published results for both models. Molmo 2 8b has 5 scored results on Noometry and Step 5 Preview has 18.