Model comparison
Claude 3 Sonnet vs Codellama 70b Instruct
Codellama 70b Instruct is the stronger model overall, scoring 33.7 to 29.0 on the Noometry Index.
Last verified . 7 shared benchmarks.
MetaSummary
- They share 7 benchmarks with published results for both. Claude 3 Sonnet scores higher in 4 categories and Codellama 70b Instruct in 1 category; 4 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Claude 3 Sonnet leads 37.8 to 24.8.
- Codellama 70b Instruct has downloadable open weights; the other is API-only.
Side by side
| Claude 3 Sonnet | Codellama 70b Instruct | |
|---|---|---|
| Provider | Anthropic | Meta |
| Noometry Index | 29.0 | 33.7 |
| Released | 2024-02-29 | — |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 30 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Codellama 70b Instruct leads
Claude 3 Sonnet: 29.6 (#302), Codellama 70b Instruct: 37.6 (#193)
| Benchmark | Claude 3 Sonnet | Codellama 70b Instruct |
|---|---|---|
| BigCodeBench Instruct | 42.7% | 40.7% |
| BigCodeBench Complete | 53.8% | 49.6% |
| HumanEval+ | 64% | 65.9% |
| WeirdML | 10.2% | — |
| LMArena Coding | 1223 | — |
| MBPP+ | 69.3% | — |
Reasoning Too close to call
Claude 3 Sonnet: 20.5 (#237), Codellama 70b Instruct: 20.1 (#242)
| Benchmark | Claude 3 Sonnet | Codellama 70b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1197 | 1052 |
| DTBench | 53.6% | — |
| Epoch Capabilities Index | 120.7 | — |
| WinoGrande | 75.1% | — |
Math Not comparable
Claude 3 Sonnet: 10.7 (#310), Codellama 70b Instruct: —
| Benchmark | Claude 3 Sonnet | Codellama 70b Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | — |
| LMArena Math | 1213 | — |
| MATH Level 5 | 18.2% | — |
Knowledge Not comparable
Claude 3 Sonnet: 21.1 (#276), Codellama 70b Instruct: —
| Benchmark | Claude 3 Sonnet | Codellama 70b Instruct |
|---|---|---|
| GPQA Diamond | 40.6% | — |
| LMArena Expert | 1173 | — |
| MMLU | 75.9% | — |
Multimodal Not comparable
Claude 3 Sonnet: 25.2 (#125), Codellama 70b Instruct: —
| Benchmark | Claude 3 Sonnet | Codellama 70b Instruct |
|---|---|---|
| LMArena Vision | 984 | — |
Multilingual Claude 3 Sonnet leads
Claude 3 Sonnet: 37.8 (#234), Codellama 70b Instruct: 24.8 (#288)
| Benchmark | Claude 3 Sonnet | Codellama 70b Instruct |
|---|---|---|
| LMArena Non-English | 1205 | 992 |
| LMArena Chinese | 1189 | — |
| LMArena French | 1229 | — |
| LMArena German | 1204 | — |
| LMArena Japanese | 1131 | — |
| LMArena Korean | 1128 | — |
| LMArena Russian | 1227 | — |
| LMArena Spanish | 1204 | — |
Instruction Following Claude 3 Sonnet leads
Claude 3 Sonnet: 62.8 (#235), Codellama 70b Instruct: 51.9 (#293)
| Benchmark | Claude 3 Sonnet | Codellama 70b Instruct |
|---|---|---|
| LMArena Instruction Following | 1199 | 1024 |
Long Context Not comparable
Claude 3 Sonnet: 36.7 (#228), Codellama 70b Instruct: —
| Benchmark | Claude 3 Sonnet | Codellama 70b Instruct |
|---|---|---|
| LMArena Longer Query | 1211 | — |
Writing & Preference Claude 3 Sonnet leads
Claude 3 Sonnet: 42.1 (#238), Codellama 70b Instruct: 33.4 (#277)
| Benchmark | Claude 3 Sonnet | Codellama 70b Instruct |
|---|---|---|
| LMArena Text | 1218 | 1057 |
| LMArena Creative Writing | 1186 | — |
| LMArena Multi-Turn | 1227 | — |
Frequently asked questions
Is Claude 3 Sonnet better than Codellama 70b Instruct?
Codellama 70b Instruct is the stronger model overall, scoring 33.7 to 29.0 on the Noometry Index.
Is Claude 3 Sonnet or Codellama 70b Instruct better for coding?
Codellama 70b Instruct scores higher on coding benchmarks: 37.6 versus 29.6 in the Noometry coding category.
How many benchmarks do Claude 3 Sonnet and Codellama 70b Instruct share?
7 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and Codellama 70b Instruct has 7.