LLaMA-13B
LLaMA-13B.
Meta Released 24 Feb 2023 14
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Meta Feb 2023 LLaMA-13B
Open weights
100.5
#247 of 271
Epoch Capabilities Index
- LAMBADA 75.2% #12 /26
- ScienceQA 43.3% #21 /23
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Knowledge and language
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| HellaSwag | 79.2% | #30 of 74 | Epoch AI | |
| LAMBADA | 75.2% | #12 of 26 | Epoch AI | |
| TriviaQA | 77.9% | #19 of 38 | Epoch AI | |
| WinoGrande | 73% | #39 of 76 | Epoch AI | |
| BoolQ | 78.7% | #41 of 75 | Epoch AI | |
| OpenBookQA | 56.4% | #23 of 41 | Epoch AI | |
| ARC-Challenge | 52.7% | #44 of 75 | Epoch AI | |
| PIQA | 80.1% | #36 of 58 | Epoch AI | |
| BIG-Bench Hard | 37.9% | #35 of 45 | Epoch AI | |
| MMLU | 47.7% | #103 of 127 | Epoch AI | |
| LMArena (Elo) | 975 | #332 of 333 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| GSM8K | 20.6% | #64 of 82 | Epoch AI |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| ScienceQA | 43.3% | #21 of 23 | Epoch AI |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| HELM Classic | 59.5 | #10 of 17 | Official leaderboard |
Meta's models over time
Meta's models in color, against every other model on the Epoch Capabilities Index, by release date.