Model comparison
Claude 3 Sonnet vs Llama 3-70B
Claude 3 Sonnet and Llama 3-70B score almost the same on the Noometry Index (29.0 vs 28.8), so choose on price, context window or the category you care about most.
Last verified . 28 shared benchmarks.
MetaSummary
- They share 28 benchmarks with published results for both. Claude 3 Sonnet scores higher in 5 categories and Llama 3-70B in 3 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in coding, where Llama 3-70B leads 35.8 to 29.6.
- Llama 3-70B has downloadable open weights; the other is API-only.
Side by side
| Claude 3 Sonnet | Llama 3-70B | |
|---|---|---|
| Provider | Anthropic | Meta |
| Noometry Index | 29.0 | 28.8 |
| Released | 2024-02-29 | 2024-04-18 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 30 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 3-70B leads
Claude 3 Sonnet: 29.6 (#302), Llama 3-70B: 35.8 (#218)
| Benchmark | Claude 3 Sonnet | Llama 3-70B |
|---|---|---|
| BigCodeBench Instruct | 42.7% | 43.6% |
| LMArena Coding | 1223 | 1206 |
| BigCodeBench Complete | 53.8% | 54.5% |
| HumanEval+ | 64% | 72% |
| MBPP+ | 69.3% | 69% |
| WeirdML | 10.2% | — |
Agentic & Tool Use Not comparable
Claude 3 Sonnet: —, Llama 3-70B: 21.1 (#139)
| Benchmark | Claude 3 Sonnet | Llama 3-70B |
|---|---|---|
| Cybench | — | 5% |
Reasoning Claude 3 Sonnet leads
Claude 3 Sonnet: 20.5 (#237), Llama 3-70B: 18.0 (#288)
| Benchmark | Claude 3 Sonnet | Llama 3-70B |
|---|---|---|
| LMArena Hard Prompts | 1197 | 1195 |
| DTBench | 53.6% | 54.2% |
| Epoch Capabilities Index | 120.7 | 122.93 |
| WinoGrande | 75.1% | 83.5% |
| Kagi LLM Benchmark | — | 35.1% |
| ForecastBench | — | 57.1 |
Math Llama 3-70B leads
Claude 3 Sonnet: 10.7 (#310), Llama 3-70B: 12.8 (#305)
| Benchmark | Claude 3 Sonnet | Llama 3-70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | 4.3% |
| LMArena Math | 1213 | 1218 |
| MATH Level 5 | 18.2% | 22.6% |
Knowledge Too close to call
Claude 3 Sonnet: 21.1 (#276), Llama 3-70B: 20.8 (#277)
| Benchmark | Claude 3 Sonnet | Llama 3-70B |
|---|---|---|
| GPQA Diamond | 40.6% | 40.6% |
| LMArena Expert | 1173 | 1149 |
| MMLU | 75.9% | 79.3% |
Multimodal Not comparable
Claude 3 Sonnet: 25.2 (#125), Llama 3-70B: —
| Benchmark | Claude 3 Sonnet | Llama 3-70B |
|---|---|---|
| LMArena Vision | 984 | — |
Multilingual Claude 3 Sonnet leads
Claude 3 Sonnet: 37.8 (#234), Llama 3-70B: 33.6 (#251)
| Benchmark | Claude 3 Sonnet | Llama 3-70B |
|---|---|---|
| LMArena Non-English | 1205 | 1142 |
| LMArena Chinese | 1189 | 1114 |
| LMArena French | 1229 | 1232 |
| LMArena German | 1204 | 1169 |
| LMArena Japanese | 1131 | 1017 |
| LMArena Korean | 1128 | 1017 |
| LMArena Russian | 1227 | 1159 |
| LMArena Spanish | 1204 | 1241 |
Instruction Following Too close to call
Claude 3 Sonnet: 62.8 (#235), Llama 3-70B: 62.5 (#238)
| Benchmark | Claude 3 Sonnet | Llama 3-70B |
|---|---|---|
| LMArena Instruction Following | 1199 | 1194 |
Long Context Claude 3 Sonnet leads
Claude 3 Sonnet: 36.7 (#228), Llama 3-70B: 35.6 (#240)
| Benchmark | Claude 3 Sonnet | Llama 3-70B |
|---|---|---|
| LMArena Longer Query | 1211 | 1174 |
Writing & Preference Too close to call
Claude 3 Sonnet: 42.1 (#238), Llama 3-70B: 42.8 (#231)
| Benchmark | Claude 3 Sonnet | Llama 3-70B |
|---|---|---|
| LMArena Text | 1218 | 1221 |
| LMArena Creative Writing | 1186 | 1210 |
| LMArena Multi-Turn | 1227 | 1223 |
Frequently asked questions
Is Claude 3 Sonnet better than Llama 3-70B?
Claude 3 Sonnet and Llama 3-70B score almost the same on the Noometry Index (29.0 vs 28.8), so choose on price, context window or the category you care about most.
Is Claude 3 Sonnet or Llama 3-70B better for coding?
Llama 3-70B scores higher on coding benchmarks: 35.8 versus 29.6 in the Noometry coding category.
How many benchmarks do Claude 3 Sonnet and Llama 3-70B share?
28 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and Llama 3-70B has 31.