Model comparison
Codellama 34b Instruct vs Phi 3 Small 8k Instruct
Codellama 34b Instruct is the stronger model overall, scoring 30.8 to 29.3 on the Noometry Index.
Last verified . 10 shared benchmarks.
Meta
MicrosoftSummary
- They share 10 benchmarks with published results for both. Codellama 34b Instruct scores higher in 4 categories and Phi 3 Small 8k Instruct in 3 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Codellama 34b Instruct leads 19.6 to 14.8.
Side by side
| Codellama 34b Instruct | Phi 3 Small 8k Instruct | |
|---|---|---|
| Provider | Meta | Microsoft |
| Noometry Index | 30.8 | 29.3 |
| Released | — | 2024-04-23 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 14 | 32 |
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 Small 8k Instruct: 27.9 (#318)
| Benchmark | Codellama 34b Instruct | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Coding | 1046 | 1101 |
| BigCodeBench Instruct | 29% | — |
| LiveBench Coding | — | 20.3% |
| BigCodeBench Complete | 37.1% | — |
| HumanEval+ | 43.9% | — |
| MBPP+ | 56.3% | — |
Reasoning Codellama 34b Instruct leads
Codellama 34b Instruct: 19.6 (#255), Phi 3 Small 8k Instruct: 14.8 (#323)
| Benchmark | Codellama 34b Instruct | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1032 | 1100 |
| LiveBench Reasoning | — | 15.9% |
| LiveBench Data Analysis | — | 30.3% |
| Adversarial NLI | — | 58.1% |
| BIG-Bench Hard | — | 79.1% |
| HellaSwag | — | 77% |
| LiveBench | — | 24% |
| WinoGrande | — | 81.5% |
Math Codellama 34b Instruct leads
Codellama 34b Instruct: 31.0 (#230), Phi 3 Small 8k Instruct: 27.6 (#248)
| Benchmark | Codellama 34b Instruct | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Math | 1056 | 1151 |
| LiveBench Math | — | 17.6% |
Knowledge Not comparable
Codellama 34b Instruct: —, Phi 3 Small 8k Instruct: 29.1 (#240)
| Benchmark | Codellama 34b Instruct | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Expert | — | 1067 |
| ARC (AI2) Challenge | — | 90.7% |
| MMLU | — | 75.7% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 58.1% |
Multilingual Phi 3 Small 8k Instruct leads
Codellama 34b Instruct: 25.8 (#284), Phi 3 Small 8k Instruct: 28.5 (#272)
| Benchmark | Codellama 34b Instruct | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Non-English | 1011 | 1058 |
| LMArena Chinese | 976 | 1061 |
| LMArena French | — | 1135 |
| LMArena German | — | 1080 |
| LMArena Japanese | — | 966 |
| LMArena Korean | — | 894 |
| LMArena Russian | — | 1111 |
| LMArena Spanish | — | 1111 |
Instruction Following Too close to call
Codellama 34b Instruct: 52.2 (#291), Phi 3 Small 8k Instruct: 51.9 (#292)
| Benchmark | Codellama 34b Instruct | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Instruction Following | 1028 | 1087 |
| LiveBench Instruction Following | — | 47.2% |
Long Context Phi 3 Small 8k Instruct leads
Codellama 34b Instruct: 30.9 (#284), Phi 3 Small 8k Instruct: 33.0 (#267)
| Benchmark | Codellama 34b Instruct | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Longer Query | 1013 | 1088 |
Writing & Preference Phi 3 Small 8k Instruct leads
Codellama 34b Instruct: 28.2 (#297), Phi 3 Small 8k Instruct: 31.1 (#284)
| Benchmark | Codellama 34b Instruct | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Text | 1066 | 1110 |
| LMArena Creative Writing | 1032 | 1083 |
| LMArena Multi-Turn | 1015 | 1068 |
| LiveBench Language | — | 12.9% |
Frequently asked questions
Is Codellama 34b Instruct better than Phi 3 Small 8k Instruct?
Codellama 34b Instruct is the stronger model overall, scoring 30.8 to 29.3 on the Noometry Index.
Is Codellama 34b Instruct or Phi 3 Small 8k Instruct better for coding?
They score almost the same on coding (28.5 vs 27.9); test both on your own repository before choosing.
How many benchmarks do Codellama 34b Instruct and Phi 3 Small 8k Instruct share?
10 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and Phi 3 Small 8k Instruct has 32.