Model comparison
Codellama 34b Instruct vs Step 5 Preview
Step 5 Preview is the stronger model overall, scoring 47.9 to 30.8 on the Noometry Index.
Last verified . 10 shared benchmarks.
Meta
StepFunSummary
- They share 10 benchmarks with published results for both. Codellama 34b Instruct scores higher in 0 categories and Step 5 Preview in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Step 5 Preview leads 62.8 to 28.2.
- Codellama 34b Instruct has downloadable open weights; the other is API-only.
Side by side
| Codellama 34b Instruct | Step 5 Preview | |
|---|---|---|
| Provider | Meta | StepFun |
| Noometry Index | 30.8 | 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 | 14 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 5 Preview leads
Codellama 34b Instruct: 28.5 (#314), Step 5 Preview: 51.8 (#36)
| Benchmark | Codellama 34b Instruct | Step 5 Preview |
|---|---|---|
| LMArena Coding | 1046 | 1480 |
| LMArena WebDev | — | 1564 |
| SciCode | — | 58.9% |
| BigCodeBench Instruct | 29% | — |
| BigCodeBench Complete | 37.1% | — |
| HumanEval+ | 43.9% | — |
| MBPP+ | 56.3% | — |
Reasoning Step 5 Preview leads
Codellama 34b Instruct: 19.6 (#255), Step 5 Preview: 40.0 (#57)
| Benchmark | Codellama 34b Instruct | Step 5 Preview |
|---|---|---|
| LMArena Hard Prompts | 1032 | 1465 |
| CritPt | — | 20.9% |
Math Step 5 Preview leads
Codellama 34b Instruct: 31.0 (#230), Step 5 Preview: 46.1 (#72)
| Benchmark | Codellama 34b Instruct | Step 5 Preview |
|---|---|---|
| LMArena Math | 1056 | 1470 |
| ProofBench | — | 42% |
Knowledge Not comparable
Codellama 34b Instruct: —, Step 5 Preview: 41.2 (#112)
| Benchmark | Codellama 34b Instruct | Step 5 Preview |
|---|---|---|
| LMArena Expert | — | 1470 |
Multimodal Not comparable
Codellama 34b Instruct: —, Step 5 Preview: 41.0 (#41)
| Benchmark | Codellama 34b Instruct | Step 5 Preview |
|---|---|---|
| LMArena Vision | — | 1267 |
Multilingual Step 5 Preview leads
Codellama 34b Instruct: 25.8 (#284), Step 5 Preview: 53.8 (#54)
| Benchmark | Codellama 34b Instruct | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1011 | 1432 |
| LMArena Chinese | 976 | 1519 |
| LMArena Russian | — | 1436 |
| LMArena Spanish | — | 1439 |
Instruction Following Step 5 Preview leads
Codellama 34b Instruct: 52.2 (#291), Step 5 Preview: 76.0 (#50)
| Benchmark | Codellama 34b Instruct | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1028 | 1444 |
Long Context Step 5 Preview leads
Codellama 34b Instruct: 30.9 (#284), Step 5 Preview: 44.5 (#64)
| Benchmark | Codellama 34b Instruct | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1013 | 1455 |
Writing & Preference Step 5 Preview leads
Codellama 34b Instruct: 28.2 (#297), Step 5 Preview: 62.8 (#71)
| Benchmark | Codellama 34b Instruct | Step 5 Preview |
|---|---|---|
| LMArena Text | 1066 | 1442 |
| LMArena Creative Writing | 1032 | 1410 |
| LMArena Multi-Turn | 1015 | 1447 |
Frequently asked questions
Is Codellama 34b Instruct better than Step 5 Preview?
Step 5 Preview is the stronger model overall, scoring 47.9 to 30.8 on the Noometry Index.
Is Codellama 34b Instruct or Step 5 Preview better for coding?
Step 5 Preview scores higher on coding benchmarks: 51.8 versus 28.5 in the Noometry coding category.
How many benchmarks do Codellama 34b Instruct and Step 5 Preview share?
10 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and Step 5 Preview has 18.