Model comparison
Codellama 70b Instruct vs Phi-4 Mini
Codellama 70b Instruct is the stronger model overall, scoring 33.3 to 30.4 on the Noometry Index.
Last verified . 0 shared benchmarks.
Meta
MicrosoftSummary
- The widest gap is in coding, where Codellama 70b Instruct leads 37.0 to 27.6.
Side by side
| Codellama 70b Instruct | Phi-4 Mini | |
|---|---|---|
| Provider | Meta | Microsoft |
| Noometry Index | 33.3 | 30.4 |
| Released | — | 2024-12-11 |
| Weights | Open | Open |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $0.075 |
| Output $ / M tokens | — | $0.30 |
| Results tracked | 7 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Codellama 70b Instruct leads
Codellama 70b Instruct: 37.0 (#189), Phi-4 Mini: 27.6 (#312)
| Benchmark | Codellama 70b Instruct | Phi-4 Mini |
|---|---|---|
| SciCode | — | 10.8% |
| BigCodeBench Instruct | 40.7% | — |
| BigCodeBench Complete | 49.6% | — |
| HumanEval+ | 65.9% | — |
Reasoning Phi-4 Mini leads
Codellama 70b Instruct: 19.2 (#241), Phi-4 Mini: 21.7 (#190)
| Benchmark | Codellama 70b Instruct | Phi-4 Mini |
|---|---|---|
| CritPt | — | 0% |
| LMArena Hard Prompts | 1052 | — |
Knowledge Not comparable
Codellama 70b Instruct: —, Phi-4 Mini: 24.8 (#261)
| Benchmark | Codellama 70b Instruct | Phi-4 Mini |
|---|---|---|
| Vectara Hallucination Rate | — | 23.5% |
Multilingual Not comparable
Codellama 70b Instruct: 24.9 (#283), Phi-4 Mini: —
| Benchmark | Codellama 70b Instruct | Phi-4 Mini |
|---|---|---|
| LMArena Non-English | 992 | — |
Instruction Following Not comparable
Codellama 70b Instruct: 52.1 (#288), Phi-4 Mini: —
| Benchmark | Codellama 70b Instruct | Phi-4 Mini |
|---|---|---|
| LMArena Instruction Following | 1024 | — |
Writing & Preference Not comparable
Codellama 70b Instruct: 33.6 (#272), Phi-4 Mini: —
| Benchmark | Codellama 70b Instruct | Phi-4 Mini |
|---|---|---|
| LMArena Text | 1057 | — |
Frequently asked questions
Is Codellama 70b Instruct better than Phi-4 Mini?
Codellama 70b Instruct is the stronger model overall, scoring 33.3 to 30.4 on the Noometry Index.
Is Codellama 70b Instruct or Phi-4 Mini better for coding?
Codellama 70b Instruct scores higher on coding benchmarks: 37.0 versus 27.6 in the Noometry coding category.
How many benchmarks do Codellama 70b Instruct and Phi-4 Mini share?
0 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Phi-4 Mini has 3.