Model comparison
Claude 2.1 vs Llama 2-13B
Llama 2-13B is the stronger model overall, scoring 29.6 to 25.2 on the Noometry Index.
Last verified . 3 shared benchmarks.
MetaSummary
- They share 3 benchmarks with published results for both. Claude 2.1 scores higher in 1 category and Llama 2-13B in 3 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in math, where Llama 2-13B leads 31.1 to 10.2.
- The biggest single-benchmark swing is DTBench: 51% for Claude 2.1 and 42.2% for Llama 2-13B.
- Llama 2-13B has downloadable open weights; the other is API-only.
Side by side
| Claude 2.1 | Llama 2-13B | |
|---|---|---|
| Provider | Anthropic | Meta |
| Noometry Index | 25.2 | 29.6 |
| Released | 2023-11-21 | 2023-07-18 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 7 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 2-13B leads
Claude 2.1: 26.2 (#327), Llama 2-13B: 30.9 (#291)
| Benchmark | Claude 2.1 | Llama 2-13B |
|---|---|---|
| WeirdML | 7.1% | — |
| LMArena Coding | — | 1062 |
Reasoning Claude 2.1 leads
Claude 2.1: 21.4 (#221), Llama 2-13B: 12.8 (#337)
| Benchmark | Claude 2.1 | Llama 2-13B |
|---|---|---|
| DTBench | 51% | 42.2% |
| Epoch Capabilities Index | 119.27 | 106.17 |
| Chess Puzzles | — | 0% |
| LMArena Hard Prompts | — | 1051 |
| BIG-Bench Hard | — | 58.2% |
| ForecastBench | 54.2 | — |
| HellaSwag | — | 80.7% |
| LAMBADA | — | 76.5% |
| PIQA | — | 80.8% |
| WinoGrande | — | 72.8% |
Math Llama 2-13B leads
Claude 2.1: 10.2 (#315), Llama 2-13B: 31.1 (#229)
| Benchmark | Claude 2.1 | Llama 2-13B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.9% | — |
| LMArena Math | — | 1065 |
| GSM8K | — | 36.9% |
Knowledge Llama 2-13B leads
Claude 2.1: 15.4 (#292), Llama 2-13B: 28.1 (#249)
| Benchmark | Claude 2.1 | Llama 2-13B |
|---|---|---|
| MMLU | 73.5% | 55.6% |
| GPQA Diamond | 33% | — |
| LMArena Expert | — | 1030 |
| ARC (AI2) Challenge | — | 60.3% |
| BoolQ | — | 82.4% |
| OpenBookQA | — | 57% |
| TriviaQA | — | 79.6% |
Multimodal Not comparable
Claude 2.1: —, Llama 2-13B: —
| Benchmark | Claude 2.1 | Llama 2-13B |
|---|---|---|
| ScienceQA | — | 55.8% |
Multilingual Not comparable
Claude 2.1: —, Llama 2-13B: 26.5 (#279)
| Benchmark | Claude 2.1 | Llama 2-13B |
|---|---|---|
| LMArena Non-English | — | 1024 |
| LMArena Chinese | — | 1001 |
| LMArena French | — | 1044 |
| LMArena German | — | 1009 |
| LMArena Japanese | — | 894 |
| LMArena Korean | — | 953 |
| LMArena Russian | — | 1055 |
| LMArena Spanish | — | 1087 |
Instruction Following Not comparable
Claude 2.1: —, Llama 2-13B: 53.3 (#287)
| Benchmark | Claude 2.1 | Llama 2-13B |
|---|---|---|
| LMArena Instruction Following | — | 1045 |
Long Context Not comparable
Claude 2.1: —, Llama 2-13B: 32.3 (#269)
| Benchmark | Claude 2.1 | Llama 2-13B |
|---|---|---|
| LMArena Longer Query | — | 1064 |
Writing & Preference Not comparable
Claude 2.1: —, Llama 2-13B: 29.8 (#289)
| Benchmark | Claude 2.1 | Llama 2-13B |
|---|---|---|
| LMArena Text | — | 1084 |
| LMArena Creative Writing | — | 1047 |
| LMArena Multi-Turn | — | 1050 |
Frequently asked questions
Is Claude 2.1 better than Llama 2-13B?
Llama 2-13B is the stronger model overall, scoring 29.6 to 25.2 on the Noometry Index.
Is Claude 2.1 or Llama 2-13B better for coding?
Llama 2-13B scores higher on coding benchmarks: 30.9 versus 26.2 in the Noometry coding category.
How many benchmarks do Claude 2.1 and Llama 2-13B share?
3 benchmarks have published results for both models. Claude 2.1 has 7 scored results on Noometry and Llama 2-13B has 32.