Model comparison
Codellama 34b Instruct vs Step 3
Step 3 is the stronger model overall, scoring 40.5 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 3 in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Step 3 leads 54.3 to 28.2.
Side by side
| Codellama 34b Instruct | Step 3 | |
|---|---|---|
| Provider | Meta | StepFun |
| Noometry Index | 30.8 | 40.5 |
| Released | — | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 14 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3 leads
Codellama 34b Instruct: 28.5 (#314), Step 3: 40.1 (#147)
| Benchmark | Codellama 34b Instruct | Step 3 |
|---|---|---|
| LMArena Coding | 1046 | 1367 |
| BigCodeBench Instruct | 29% | — |
| BigCodeBench Complete | 37.1% | — |
| HumanEval+ | 43.9% | — |
| MBPP+ | 56.3% | — |
Reasoning Step 3 leads
Codellama 34b Instruct: 19.6 (#255), Step 3: 28.4 (#105)
| Benchmark | Codellama 34b Instruct | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1032 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |
Math Step 3 leads
Codellama 34b Instruct: 31.0 (#230), Step 3: 37.6 (#148)
| Benchmark | Codellama 34b Instruct | Step 3 |
|---|---|---|
| LMArena Math | 1056 | 1366 |
Knowledge Not comparable
Codellama 34b Instruct: —, Step 3: 36.8 (#164)
| Benchmark | Codellama 34b Instruct | Step 3 |
|---|---|---|
| LMArena Expert | — | 1333 |
Multimodal Not comparable
Codellama 34b Instruct: —, Step 3: 35.5 (#86)
| Benchmark | Codellama 34b Instruct | Step 3 |
|---|---|---|
| LMArena Vision | — | 1177 |
Multilingual Step 3 leads
Codellama 34b Instruct: 25.8 (#284), Step 3: 46.3 (#159)
| Benchmark | Codellama 34b Instruct | Step 3 |
|---|---|---|
| LMArena Non-English | 1011 | 1327 |
| LMArena Chinese | 976 | 1397 |
| LMArena German | — | 1371 |
| LMArena Korean | — | 1269 |
| LMArena Russian | — | 1331 |
| LMArena Spanish | — | 1371 |
Instruction Following Step 3 leads
Codellama 34b Instruct: 52.2 (#291), Step 3: 70.4 (#164)
| Benchmark | Codellama 34b Instruct | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1028 | 1332 |
Long Context Step 3 leads
Codellama 34b Instruct: 30.9 (#284), Step 3: 40.3 (#157)
| Benchmark | Codellama 34b Instruct | Step 3 |
|---|---|---|
| LMArena Longer Query | 1013 | 1326 |
Writing & Preference Step 3 leads
Codellama 34b Instruct: 28.2 (#297), Step 3: 54.3 (#151)
| Benchmark | Codellama 34b Instruct | Step 3 |
|---|---|---|
| LMArena Text | 1066 | 1350 |
| LMArena Creative Writing | 1032 | 1321 |
| LMArena Multi-Turn | 1015 | 1341 |
Frequently asked questions
Is Codellama 34b Instruct better than Step 3?
Step 3 is the stronger model overall, scoring 40.5 to 30.8 on the Noometry Index.
Is Codellama 34b Instruct or Step 3 better for coding?
Step 3 scores higher on coding benchmarks: 40.1 versus 28.5 in the Noometry coding category.
How many benchmarks do Codellama 34b Instruct and Step 3 share?
10 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and Step 3 has 17.