Model comparison
Codellama 34b Instruct vs Phi 3 Mini 128k Instruct
Codellama 34b Instruct is the stronger model overall, scoring 30.8 to 29.7 on the Noometry Index.
Last verified . 12 shared benchmarks.
Meta
MicrosoftSummary
- They share 12 benchmarks with published results for both. Codellama 34b Instruct scores higher in 5 categories and Phi 3 Mini 128k Instruct in 2 categories; one gap is clear of the uncertainty.
Side by side
| Codellama 34b Instruct | Phi 3 Mini 128k Instruct | |
|---|---|---|
| Provider | Meta | Microsoft |
| Noometry Index | 30.8 | 29.7 |
| Released | — | 2024-04-23 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 14 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Codellama 34b Instruct: 28.5 (#314), Phi 3 Mini 128k Instruct: 28.8 (#312)
| Benchmark | Codellama 34b Instruct | Phi 3 Mini 128k Instruct |
|---|---|---|
| BigCodeBench Instruct | 29% | 29.6% |
| LMArena Coding | 1046 | 1039 |
| BigCodeBench Complete | 37.1% | 40.6% |
| HumanEval+ | 43.9% | — |
| MBPP+ | 56.3% | — |
Reasoning Too close to call
Codellama 34b Instruct: 19.6 (#255), Phi 3 Mini 128k Instruct: 19.6 (#256)
| Benchmark | Codellama 34b Instruct | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1032 | 1028 |
Math Too close to call
Codellama 34b Instruct: 31.0 (#230), Phi 3 Mini 128k Instruct: 31.6 (#222)
| Benchmark | Codellama 34b Instruct | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Math | 1056 | 1089 |
Knowledge Not comparable
Codellama 34b Instruct: —, Phi 3 Mini 128k Instruct: 26.8 (#254)
| Benchmark | Codellama 34b Instruct | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Expert | — | 984 |
Multilingual Too close to call
Codellama 34b Instruct: 25.8 (#284), Phi 3 Mini 128k Instruct: 25.2 (#285)
| Benchmark | Codellama 34b Instruct | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Non-English | 1011 | 1000 |
| LMArena Chinese | 976 | 1016 |
| LMArena French | — | 1039 |
| LMArena German | — | 1006 |
| LMArena Japanese | — | 899 |
| LMArena Korean | — | 856 |
| LMArena Russian | — | 1004 |
| LMArena Spanish | — | 1059 |
Instruction Following Too close to call
Codellama 34b Instruct: 52.2 (#291), Phi 3 Mini 128k Instruct: 51.8 (#294)
| Benchmark | Codellama 34b Instruct | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Instruction Following | 1028 | 1023 |
Long Context Too close to call
Codellama 34b Instruct: 30.9 (#284), Phi 3 Mini 128k Instruct: 30.4 (#289)
| Benchmark | Codellama 34b Instruct | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Longer Query | 1013 | 996 |
Writing & Preference Codellama 34b Instruct leads
Codellama 34b Instruct: 28.2 (#297), Phi 3 Mini 128k Instruct: 27.1 (#301)
| Benchmark | Codellama 34b Instruct | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Text | 1066 | 1050 |
| LMArena Creative Writing | 1032 | 1024 |
| LMArena Multi-Turn | 1015 | 989 |
Frequently asked questions
Is Codellama 34b Instruct better than Phi 3 Mini 128k Instruct?
Codellama 34b Instruct is the stronger model overall, scoring 30.8 to 29.7 on the Noometry Index.
Is Codellama 34b Instruct or Phi 3 Mini 128k Instruct better for coding?
They score almost the same on coding (28.5 vs 28.8); test both on your own repository before choosing.
How many benchmarks do Codellama 34b Instruct and Phi 3 Mini 128k Instruct share?
12 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and Phi 3 Mini 128k Instruct has 19.