# Codellama 70b Instruct vs Phi-4

> Codellama 70b Instruct is the stronger model overall, scoring 33.7 to 31.2 on the Noometry Index.

- Canonical page: https://noometry.com/compare/codellama-70b-instruct-vs-phi-4
- Last updated: 2026-10-10
- Shared benchmarks: 6

## Summary

- They share 6 benchmarks with published results for both. Codellama 70b Instruct scores higher in 2 categories and Phi-4 in 3 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Phi-4 leads 37.2 to 24.8.
- The biggest single-benchmark swing is BigCodeBench Complete: 49.6% for Codellama 70b Instruct and 55.4% for Phi-4.

## Snapshot

| | Codellama 70b Instruct | Phi-4 |
|---|---|---|
| Provider | Meta | Microsoft |
| Noometry Index | 33.7 | 31.2 |
| Rank | 237 | 279 |
| Context | — | 128K |
| Input $/M | — | $0.07 |
| Output $/M | — | $0.14 |
| Weights | Open | Open |

## Coding

- Codellama 70b Instruct: 37.6 (#193)
- Phi-4: 34.4 (#239)

| Benchmark | Codellama 70b Instruct | Phi-4 |
|---|---|---|
| BigCodeBench Instruct | 40.7% | 45.5% |
| BigCodeBench Complete | 49.6% | 55.4% |
| LiveBench Coding | — | 30.7% |
| LMArena Coding | — | 1231 |
| HumanEval+ | 65.9% | — |

## Agentic & Tool Use

- Codellama 70b Instruct: —
- Phi-4: 22.8 (#128)

| Benchmark | Codellama 70b Instruct | Phi-4 |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 28.8% |
| BALROG | — | 11.6% |

## Reasoning

- Codellama 70b Instruct: 20.1 (#242)
- Phi-4: 17.7 (#291)

| Benchmark | Codellama 70b Instruct | Phi-4 |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1220 |
| Chess Puzzles | — | 1% |
| LiveBench Reasoning | — | 47.8% |
| LiveBench Data Analysis | — | 45.2% |
| Epoch Capabilities Index | — | 130.42 |
| LiveBench | — | 41.6% |

## Math

- Codellama 70b Instruct: —
- Phi-4: 20.8 (#285)

| Benchmark | Codellama 70b Instruct | Phi-4 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 13.8% |
| LiveBench Math | — | 42% |
| LMArena Math | — | 1246 |
| MATH Level 5 | — | 64.9% |

## Knowledge

- Codellama 70b Instruct: —
- Phi-4: 32.6 (#209)

| Benchmark | Codellama 70b Instruct | Phi-4 |
|---|---|---|
| GPQA Diamond | — | 56.1% |
| Confabulations | — | 29.4% |
| Vectara Hallucination Rate | — | 3.7% |
| LMArena Expert | — | 1203 |
| MMLU | — | 84.8% |

## Multilingual

- Codellama 70b Instruct: 24.8 (#288)
- Phi-4: 37.2 (#237)

| Benchmark | Codellama 70b Instruct | Phi-4 |
|---|---|---|
| LMArena Non-English | 992 | 1197 |
| LMArena Chinese | — | 1212 |
| LMArena French | — | 1224 |
| LMArena German | — | 1222 |
| LMArena Japanese | — | 1158 |
| LMArena Korean | — | 1151 |
| LMArena Russian | — | 1209 |
| LMArena Spanish | — | 1234 |

## Instruction Following

- Codellama 70b Instruct: 51.9 (#293)
- Phi-4: 60.4 (#251)

| Benchmark | Codellama 70b Instruct | Phi-4 |
|---|---|---|
| LMArena Instruction Following | 1024 | 1201 |
| LiveBench Instruction Following | — | 58.4% |

## Long Context

- Codellama 70b Instruct: —
- Phi-4: 36.9 (#226)

| Benchmark | Codellama 70b Instruct | Phi-4 |
|---|---|---|
| LMArena Longer Query | — | 1217 |

## Writing & Preference

- Codellama 70b Instruct: 33.4 (#277)
- Phi-4: 40.5 (#244)

| Benchmark | Codellama 70b Instruct | Phi-4 |
|---|---|---|
| LMArena Text | 1057 | 1217 |
| LMArena Creative Writing | — | 1182 |
| Short-Story Creative Writing | — | 62.6% |
| LMArena Multi-Turn | — | 1206 |
| LiveBench Language | — | 25.6% |

## FAQ

### Is Codellama 70b Instruct better than Phi-4?

Codellama 70b Instruct is the stronger model overall, scoring 33.7 to 31.2 on the Noometry Index.

### Is Codellama 70b Instruct or Phi-4 better for coding?

Codellama 70b Instruct scores higher on coding benchmarks: 37.6 versus 34.4 in the Noometry coding category.

### How many benchmarks do Codellama 70b Instruct and Phi-4 share?

6 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Phi-4 has 37.