Model comparison
Codellama 34b Instruct vs Phi-2
Codellama 34b Instruct has enough public results to be ranked (#285); Phi-2 does not yet, so treat this comparison as directional.
Last verified . 2 shared benchmarks.
Meta
MicrosoftSummary
- They share 2 benchmarks with published results for both.
Side by side
| Codellama 34b Instruct | Phi-2 | |
|---|---|---|
| Provider | Meta | Microsoft |
| Noometry Index | 30.2 | — |
| Released | — | 2023-12-12 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 14 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Codellama 34b Instruct: 28.0 (#310), Phi-2: —
| Benchmark | Codellama 34b Instruct | Phi-2 |
|---|---|---|
| HumanEval+ | 43.9% | 45.1% |
| MBPP+ | 56.3% | 54.2% |
| BigCodeBench Instruct | 29% | — |
| LMArena Coding | 1046 | — |
| BigCodeBench Complete | 37.1% | — |
Reasoning Not comparable
Codellama 34b Instruct: 18.8 (#250), Phi-2: —
| Benchmark | Codellama 34b Instruct | Phi-2 |
|---|---|---|
| LMArena Hard Prompts | 1032 | — |
| Adversarial NLI | — | 42.5% |
| BIG-Bench Hard | — | 59.4% |
| Epoch Capabilities Index | — | 107.62 |
| HellaSwag | — | 53.6% |
| WinoGrande | — | 54.7% |
Math Not comparable
Codellama 34b Instruct: 28.5 (#227), Phi-2: —
| Benchmark | Codellama 34b Instruct | Phi-2 |
|---|---|---|
| LMArena Math | 1056 | — |
Knowledge Not comparable
Codellama 34b Instruct: —, Phi-2: —
| Benchmark | Codellama 34b Instruct | Phi-2 |
|---|---|---|
| ARC (AI2) Challenge | — | 75.9% |
| MMLU | — | 58.4% |
| OpenBookQA | — | 73.6% |
| TriviaQA | — | 45.2% |
Multilingual Not comparable
Codellama 34b Instruct: 25.9 (#279), Phi-2: —
| Benchmark | Codellama 34b Instruct | Phi-2 |
|---|---|---|
| LMArena Non-English | 1011 | — |
| LMArena Chinese | 976 | — |
Instruction Following Not comparable
Codellama 34b Instruct: 52.4 (#286), Phi-2: —
| Benchmark | Codellama 34b Instruct | Phi-2 |
|---|---|---|
| LMArena Instruction Following | 1028 | — |
Long Context Not comparable
Codellama 34b Instruct: 30.8 (#279), Phi-2: —
| Benchmark | Codellama 34b Instruct | Phi-2 |
|---|---|---|
| LMArena Longer Query | 1014 | — |
Writing & Preference Not comparable
Codellama 34b Instruct: 28.4 (#292), Phi-2: —
| Benchmark | Codellama 34b Instruct | Phi-2 |
|---|---|---|
| LMArena Text | 1066 | — |
| LMArena Creative Writing | 1032 | — |
| LMArena Multi-Turn | 1015 | — |
Frequently asked questions
Is Codellama 34b Instruct better than Phi-2?
Codellama 34b Instruct has enough public results to be ranked (#285); Phi-2 does not yet, so treat this comparison as directional.
How many benchmarks do Codellama 34b Instruct and Phi-2 share?
2 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and Phi-2 has 11.