Model comparison
Claude 3 Sonnet vs Llama 13b
Claude 3 Sonnet is the stronger model overall, scoring 29.0 to 24.4 on the Noometry Index.
Last verified . 11 shared benchmarks.
MetaSummary
- They share 11 benchmarks with published results for both. Claude 3 Sonnet scores higher in 5 categories and Llama 13b in 1 category; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Claude 3 Sonnet leads 42.1 to 13.8.
- Llama 13b has downloadable open weights; the other is API-only.
Side by side
| Claude 3 Sonnet | Llama 13b | |
|---|---|---|
| Provider | Anthropic | Meta |
| Noometry Index | 29.0 | 24.4 |
| Released | 2024-02-29 | 2023-02-24 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 30 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude 3 Sonnet leads
Claude 3 Sonnet: 29.6 (#302), Llama 13b: 21.4 (#337)
| Benchmark | Claude 3 Sonnet | Llama 13b |
|---|---|---|
| LMArena Coding | 1223 | 683 |
| WeirdML | 10.2% | — |
| BigCodeBench Instruct | 42.7% | — |
| BigCodeBench Complete | 53.8% | — |
| HumanEval+ | 64% | — |
| MBPP+ | 69.3% | — |
Reasoning Claude 3 Sonnet leads
Claude 3 Sonnet: 20.5 (#237), Llama 13b: 14.0 (#329)
| Benchmark | Claude 3 Sonnet | Llama 13b |
|---|---|---|
| LMArena Hard Prompts | 1197 | 728 |
| Epoch Capabilities Index | 120.7 | 100.58 |
| WinoGrande | 75.1% | 73% |
| DTBench | 53.6% | — |
| BIG-Bench Hard | — | 37.9% |
| HellaSwag | — | 79.2% |
| LAMBADA | — | 75.2% |
| PIQA | — | 80.1% |
Math Llama 13b leads
Claude 3 Sonnet: 10.7 (#310), Llama 13b: 26.7 (#256)
| Benchmark | Claude 3 Sonnet | Llama 13b |
|---|---|---|
| LMArena Math | 1213 | 838 |
| OTIS Mock AIME 2024-2025 | 2.5% | — |
| MATH Level 5 | 18.2% | — |
| GSM8K | — | 20.6% |
Knowledge Not comparable
Claude 3 Sonnet: 21.1 (#276), Llama 13b: —
| Benchmark | Claude 3 Sonnet | Llama 13b |
|---|---|---|
| MMLU | 75.9% | 47.7% |
| GPQA Diamond | 40.6% | — |
| LMArena Expert | 1173 | — |
| ARC (AI2) Challenge | — | 52.7% |
| BoolQ | — | 78.7% |
| OpenBookQA | — | 56.4% |
| TriviaQA | — | 77.9% |
Multimodal Not comparable
Claude 3 Sonnet: 25.2 (#125), Llama 13b: —
| Benchmark | Claude 3 Sonnet | Llama 13b |
|---|---|---|
| LMArena Vision | 984 | — |
| ScienceQA | — | 43.3% |
Multilingual Claude 3 Sonnet leads
Claude 3 Sonnet: 37.8 (#234), Llama 13b: 16.6 (#297)
| Benchmark | Claude 3 Sonnet | Llama 13b |
|---|---|---|
| LMArena Non-English | 1205 | 819 |
| 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), Llama 13b: 36.7 (#305)
| Benchmark | Claude 3 Sonnet | Llama 13b |
|---|---|---|
| LMArena Instruction Following | 1199 | 781 |
Long Context Not comparable
Claude 3 Sonnet: 36.7 (#228), Llama 13b: —
| Benchmark | Claude 3 Sonnet | Llama 13b |
|---|---|---|
| LMArena Longer Query | 1211 | — |
Writing & Preference Claude 3 Sonnet leads
Claude 3 Sonnet: 42.1 (#238), Llama 13b: 13.8 (#312)
| Benchmark | Claude 3 Sonnet | Llama 13b |
|---|---|---|
| LMArena Text | 1218 | 834 |
| LMArena Creative Writing | 1186 | 794 |
| LMArena Multi-Turn | 1227 | 753 |
Frequently asked questions
Is Claude 3 Sonnet better than Llama 13b?
Claude 3 Sonnet is the stronger model overall, scoring 29.0 to 24.4 on the Noometry Index.
Is Claude 3 Sonnet or Llama 13b better for coding?
Claude 3 Sonnet scores higher on coding benchmarks: 29.6 versus 21.4 in the Noometry coding category.
How many benchmarks do Claude 3 Sonnet and Llama 13b share?
11 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and Llama 13b has 21.