Model comparison
Codellama 70b Instruct vs Llama 3.2 3B
Codellama 70b Instruct is the stronger model overall, scoring 33.7 to 28.9 on the Noometry Index.
Last verified . 6 shared benchmarks.
MetaSummary
- They share 6 benchmarks with published results for both. Codellama 70b Instruct scores higher in 2 categories and Llama 3.2 3B in 3 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in coding, where Codellama 70b Instruct leads 37.6 to 27.6.
- The biggest single-benchmark swing is BigCodeBench Complete: 49.6% for Codellama 70b Instruct and 28.3% for Llama 3.2 3B.
Side by side
| Codellama 70b Instruct | Llama 3.2 3B | |
|---|---|---|
| Provider | Meta | Meta |
| Noometry Index | 33.7 | 28.9 |
| Released | — | 2024-09-24 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 118K |
| Input $ / M tokens | — | $0.05 |
| Output $ / M tokens | — | $0.33 |
| Results tracked | 7 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Codellama 70b Instruct leads
Codellama 70b Instruct: 37.6 (#193), Llama 3.2 3B: 27.6 (#319)
| Benchmark | Codellama 70b Instruct | Llama 3.2 3B |
|---|---|---|
| BigCodeBench Instruct | 40.7% | 23.4% |
| BigCodeBench Complete | 49.6% | 28.3% |
| LMArena Coding | — | 1098 |
| HumanEval+ | 65.9% | — |
Agentic & Tool Use Not comparable
Codellama 70b Instruct: —, Llama 3.2 3B: 20.1 (#143)
| Benchmark | Codellama 70b Instruct | Llama 3.2 3B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 21.9% |
| BALROG | — | 10.1% |
Reasoning Too close to call
Codellama 70b Instruct: 20.1 (#242), Llama 3.2 3B: 21.0 (#228)
| Benchmark | Codellama 70b Instruct | Llama 3.2 3B |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1095 |
Math Not comparable
Codellama 70b Instruct: —, Llama 3.2 3B: 32.4 (#214)
| Benchmark | Codellama 70b Instruct | Llama 3.2 3B |
|---|---|---|
| LMArena Math | — | 1126 |
Knowledge Not comparable
Codellama 70b Instruct: —, Llama 3.2 3B: 29.7 (#235)
| Benchmark | Codellama 70b Instruct | Llama 3.2 3B |
|---|---|---|
| LMArena Expert | — | 1090 |
Multilingual Llama 3.2 3B leads
Codellama 70b Instruct: 24.8 (#288), Llama 3.2 3B: 26.2 (#281)
| Benchmark | Codellama 70b Instruct | Llama 3.2 3B |
|---|---|---|
| LMArena Non-English | 992 | 1019 |
| LMArena Chinese | — | 1017 |
| LMArena German | — | 1056 |
| LMArena Russian | — | 949 |
Instruction Following Llama 3.2 3B leads
Codellama 70b Instruct: 51.9 (#293), Llama 3.2 3B: 56.0 (#275)
| Benchmark | Codellama 70b Instruct | Llama 3.2 3B |
|---|---|---|
| LMArena Instruction Following | 1024 | 1089 |
Long Context Not comparable
Codellama 70b Instruct: —, Llama 3.2 3B: 33.4 (#261)
| Benchmark | Codellama 70b Instruct | Llama 3.2 3B |
|---|---|---|
| LMArena Longer Query | — | 1100 |
Writing & Preference Codellama 70b Instruct leads
Codellama 70b Instruct: 33.4 (#277), Llama 3.2 3B: 24.7 (#307)
| Benchmark | Codellama 70b Instruct | Llama 3.2 3B |
|---|---|---|
| LMArena Text | 1057 | 1110 |
| LMArena Creative Writing | — | 1094 |
| EQ-Bench Creative Writing | — | 595 |
| LMArena Multi-Turn | — | 1105 |
Frequently asked questions
Is Codellama 70b Instruct better than Llama 3.2 3B?
Codellama 70b Instruct is the stronger model overall, scoring 33.7 to 28.9 on the Noometry Index.
Is Codellama 70b Instruct or Llama 3.2 3B better for coding?
Codellama 70b Instruct scores higher on coding benchmarks: 37.6 versus 27.6 in the Noometry coding category.
How many benchmarks do Codellama 70b Instruct and Llama 3.2 3B share?
6 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Llama 3.2 3B has 18.