Model comparison
Claude 2.1 vs Llama 3-70B
Llama 3-70B is the stronger model overall, scoring 28.8 to 25.2 on the Noometry Index.
Last verified . 6 shared benchmarks.
MetaSummary
- They share 6 benchmarks with published results for both. Claude 2.1 scores higher in 1 category and Llama 3-70B in 3 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in coding, where Llama 3-70B leads 35.8 to 26.2.
- The biggest single-benchmark swing is GPQA Diamond: 33% for Claude 2.1 and 40.6% for Llama 3-70B.
- Llama 3-70B has downloadable open weights; the other is API-only.
Side by side
| Claude 2.1 | Llama 3-70B | |
|---|---|---|
| Provider | Anthropic | Meta |
| Noometry Index | 25.2 | 28.8 |
| Released | 2023-11-21 | 2024-04-18 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 7 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 3-70B leads
Claude 2.1: 26.2 (#327), Llama 3-70B: 35.8 (#218)
| Benchmark | Claude 2.1 | Llama 3-70B |
|---|---|---|
| WeirdML | 7.1% | — |
| BigCodeBench Instruct | — | 43.6% |
| LMArena Coding | — | 1206 |
| BigCodeBench Complete | — | 54.5% |
| HumanEval+ | — | 72% |
| MBPP+ | — | 69% |
Agentic & Tool Use Not comparable
Claude 2.1: —, Llama 3-70B: 21.1 (#139)
| Benchmark | Claude 2.1 | Llama 3-70B |
|---|---|---|
| Cybench | — | 5% |
Reasoning Claude 2.1 leads
Claude 2.1: 21.4 (#221), Llama 3-70B: 18.0 (#288)
| Benchmark | Claude 2.1 | Llama 3-70B |
|---|---|---|
| DTBench | 51% | 54.2% |
| Epoch Capabilities Index | 119.27 | 122.93 |
| ForecastBench | 54.2 | 57.1 |
| Kagi LLM Benchmark | — | 35.1% |
| LMArena Hard Prompts | — | 1195 |
| WinoGrande | — | 83.5% |
Math Llama 3-70B leads
Claude 2.1: 10.2 (#315), Llama 3-70B: 12.8 (#305)
| Benchmark | Claude 2.1 | Llama 3-70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.9% | 4.3% |
| LMArena Math | — | 1218 |
| MATH Level 5 | — | 22.6% |
Knowledge Llama 3-70B leads
Claude 2.1: 15.4 (#292), Llama 3-70B: 20.8 (#277)
| Benchmark | Claude 2.1 | Llama 3-70B |
|---|---|---|
| GPQA Diamond | 33% | 40.6% |
| MMLU | 73.5% | 79.3% |
| LMArena Expert | — | 1149 |
Multilingual Not comparable
Claude 2.1: —, Llama 3-70B: 33.6 (#251)
| Benchmark | Claude 2.1 | Llama 3-70B |
|---|---|---|
| LMArena Non-English | — | 1142 |
| LMArena Chinese | — | 1114 |
| LMArena French | — | 1232 |
| LMArena German | — | 1169 |
| LMArena Japanese | — | 1017 |
| LMArena Korean | — | 1017 |
| LMArena Russian | — | 1159 |
| LMArena Spanish | — | 1241 |
Instruction Following Not comparable
Claude 2.1: —, Llama 3-70B: 62.5 (#238)
| Benchmark | Claude 2.1 | Llama 3-70B |
|---|---|---|
| LMArena Instruction Following | — | 1194 |
Long Context Not comparable
Claude 2.1: —, Llama 3-70B: 35.6 (#240)
| Benchmark | Claude 2.1 | Llama 3-70B |
|---|---|---|
| LMArena Longer Query | — | 1174 |
Writing & Preference Not comparable
Claude 2.1: —, Llama 3-70B: 42.8 (#231)
| Benchmark | Claude 2.1 | Llama 3-70B |
|---|---|---|
| LMArena Text | — | 1221 |
| LMArena Creative Writing | — | 1210 |
| LMArena Multi-Turn | — | 1223 |
Frequently asked questions
Is Claude 2.1 better than Llama 3-70B?
Llama 3-70B is the stronger model overall, scoring 28.8 to 25.2 on the Noometry Index.
Is Claude 2.1 or Llama 3-70B better for coding?
Llama 3-70B scores higher on coding benchmarks: 35.8 versus 26.2 in the Noometry coding category.
How many benchmarks do Claude 2.1 and Llama 3-70B share?
6 benchmarks have published results for both models. Claude 2.1 has 7 scored results on Noometry and Llama 3-70B has 31.