Model comparison
Olmo 7b Instruct vs Step 5 Preview
Step 5 Preview is the stronger model overall, scoring 47.9 to 30.3 on the Noometry Index.
Last verified . 10 shared benchmarks.
Allen Institute for AI (Ai2)
StepFunSummary
- They share 10 benchmarks with published results for both. Olmo 7b Instruct scores higher in 0 categories and Step 5 Preview in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Step 5 Preview leads 62.8 to 25.8.
- Olmo 7b Instruct has downloadable open weights; the other is API-only.
Side by side
| Olmo 7b Instruct | Step 5 Preview | |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | StepFun |
| Noometry Index | 30.3 | 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 | 10 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 5 Preview leads
Olmo 7b Instruct: 29.6 (#303), Step 5 Preview: 51.8 (#36)
| Benchmark | Olmo 7b Instruct | Step 5 Preview |
|---|---|---|
| LMArena Coding | 1016 | 1480 |
| LMArena WebDev | — | 1564 |
| SciCode | — | 58.9% |
Reasoning Step 5 Preview leads
Olmo 7b Instruct: 18.8 (#274), Step 5 Preview: 40.0 (#57)
| Benchmark | Olmo 7b Instruct | Step 5 Preview |
|---|---|---|
| LMArena Hard Prompts | 993 | 1465 |
| CritPt | — | 20.9% |
Math Step 5 Preview leads
Olmo 7b Instruct: 30.2 (#237), Step 5 Preview: 46.1 (#72)
| Benchmark | Olmo 7b Instruct | Step 5 Preview |
|---|---|---|
| LMArena Math | 1018 | 1470 |
| ProofBench | — | 42% |
Knowledge Not comparable
Olmo 7b Instruct: —, Step 5 Preview: 41.2 (#112)
| Benchmark | Olmo 7b Instruct | Step 5 Preview |
|---|---|---|
| LMArena Expert | — | 1470 |
Multimodal Not comparable
Olmo 7b Instruct: —, Step 5 Preview: 41.0 (#41)
| Benchmark | Olmo 7b Instruct | Step 5 Preview |
|---|---|---|
| LMArena Vision | — | 1267 |
Multilingual Step 5 Preview leads
Olmo 7b Instruct: 24.0 (#291), Step 5 Preview: 53.8 (#54)
| Benchmark | Olmo 7b Instruct | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 977 | 1432 |
| LMArena Chinese | 1014 | 1519 |
| LMArena Russian | 947 | 1436 |
| LMArena Spanish | — | 1439 |
Instruction Following Step 5 Preview leads
Olmo 7b Instruct: 49.0 (#301), Step 5 Preview: 76.0 (#50)
| Benchmark | Olmo 7b Instruct | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 978 | 1444 |
Long Context Not comparable
Olmo 7b Instruct: —, Step 5 Preview: 44.5 (#64)
| Benchmark | Olmo 7b Instruct | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | — | 1455 |
Writing & Preference Step 5 Preview leads
Olmo 7b Instruct: 25.8 (#303), Step 5 Preview: 62.8 (#71)
| Benchmark | Olmo 7b Instruct | Step 5 Preview |
|---|---|---|
| LMArena Text | 1032 | 1442 |
| LMArena Creative Writing | 990 | 1410 |
| LMArena Multi-Turn | 1007 | 1447 |
Frequently asked questions
Is Olmo 7b Instruct better than Step 5 Preview?
Step 5 Preview is the stronger model overall, scoring 47.9 to 30.3 on the Noometry Index.
Is Olmo 7b Instruct or Step 5 Preview better for coding?
Step 5 Preview scores higher on coding benchmarks: 51.8 versus 29.6 in the Noometry coding category.
How many benchmarks do Olmo 7b Instruct and Step 5 Preview share?
10 benchmarks have published results for both models. Olmo 7b Instruct has 10 scored results on Noometry and Step 5 Preview has 18.