Model comparison
Codellama 34b Instruct vs Step 3.5 Flash
Step 3.5 Flash is the stronger model overall, scoring 42.3 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 3.5 Flash in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Step 3.5 Flash leads 58.8 to 28.2.
Side by side
| Codellama 34b Instruct | Step 3.5 Flash | |
|---|---|---|
| Provider | Meta | StepFun |
| Noometry Index | 30.8 | 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 | 14 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3.5 Flash leads
Codellama 34b Instruct: 28.5 (#314), Step 3.5 Flash: 42.4 (#105)
| Benchmark | Codellama 34b Instruct | Step 3.5 Flash |
|---|---|---|
| LMArena Coding | 1046 | 1436 |
| BigCodeBench Instruct | 29% | — |
| BigCodeBench Complete | 37.1% | — |
| HumanEval+ | 43.9% | — |
| MBPP+ | 56.3% | — |
Reasoning Step 3.5 Flash leads
Codellama 34b Instruct: 19.6 (#255), Step 3.5 Flash: 22.2 (#202)
| Benchmark | Codellama 34b Instruct | Step 3.5 Flash |
|---|---|---|
| LMArena Hard Prompts | 1032 | 1411 |
| NYT Connections (extended) | — | 28.4% |
Math Step 3.5 Flash leads
Codellama 34b Instruct: 31.0 (#230), Step 3.5 Flash: 42.6 (#84)
| Benchmark | Codellama 34b Instruct | Step 3.5 Flash |
|---|---|---|
| LMArena Math | 1056 | 1408 |
| MathArena Final-Answer Competitions | — | 66.8% |
Knowledge Not comparable
Codellama 34b Instruct: —, Step 3.5 Flash: 39.6 (#132)
| Benchmark | Codellama 34b Instruct | Step 3.5 Flash |
|---|---|---|
| LMArena Expert | — | 1421 |
Multilingual Step 3.5 Flash leads
Codellama 34b Instruct: 25.8 (#284), Step 3.5 Flash: 50.5 (#119)
| Benchmark | Codellama 34b Instruct | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | 1011 | 1385 |
| LMArena Chinese | 976 | 1447 |
| LMArena French | — | 1421 |
| LMArena German | — | 1405 |
| LMArena Japanese | — | 1354 |
| LMArena Korean | — | 1352 |
| LMArena Russian | — | 1385 |
| LMArena Spanish | — | 1419 |
Instruction Following Step 3.5 Flash leads
Codellama 34b Instruct: 52.2 (#291), Step 3.5 Flash: 73.1 (#124)
| Benchmark | Codellama 34b Instruct | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1028 | 1385 |
Long Context Step 3.5 Flash leads
Codellama 34b Instruct: 30.9 (#284), Step 3.5 Flash: 42.8 (#117)
| Benchmark | Codellama 34b Instruct | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | 1013 | 1402 |
Writing & Preference Step 3.5 Flash leads
Codellama 34b Instruct: 28.2 (#297), Step 3.5 Flash: 58.8 (#113)
| Benchmark | Codellama 34b Instruct | Step 3.5 Flash |
|---|---|---|
| LMArena Text | 1066 | 1403 |
| LMArena Creative Writing | 1032 | 1357 |
| LMArena Multi-Turn | 1015 | 1405 |
Frequently asked questions
Is Codellama 34b Instruct better than Step 3.5 Flash?
Step 3.5 Flash is the stronger model overall, scoring 42.3 to 30.8 on the Noometry Index.
Is Codellama 34b Instruct or Step 3.5 Flash better for coding?
Step 3.5 Flash scores higher on coding benchmarks: 42.4 versus 28.5 in the Noometry coding category.
How many benchmarks do Codellama 34b Instruct and Step 3.5 Flash share?
10 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and Step 3.5 Flash has 19.