Falcon-7B
Falcon-7B.
14
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Falcon-7B
Open weights
95.0
#253 of 271
Epoch Capabilities Index
- LAMBADA 74.9% #13 /26
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 | 78.1% | #32 of 74 | Epoch AI | |
| LAMBADA | 74.9% | #13 of 26 | Epoch AI | |
| PIQA | 80.3% | #34 of 58 | Epoch AI | |
| OpenBookQA | 51.6% | #26 of 41 | Epoch AI | |
| ARC-Challenge | 47.9% | #48 of 75 | Epoch AI | |
| BoolQ | 75.3% | #50 of 75 | Epoch AI | |
| WinoGrande | 67.2% | #54 of 76 | Epoch AI | |
| TriviaQA | 64.6% | #32 of 38 | Epoch AI | |
| MMLU | 35% | #118 of 127 | Epoch AI | |
| BIG-Bench Hard | 28.8% | #44 of 45 | Epoch AI | |
| AlpacaEval 2.0 | 4.04% | #40 of 40 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| GSM8K | 6.80% | #73 of 82 | Epoch AI |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| HELM Classic | 37.8 | #14 of 17 | Official leaderboard | |
| HELM Lite | 6.45 | #71 of 71 | Official leaderboard |
Technology Innovation Institute's models over time
Technology Innovation Institute's models in color, against every other model on the Epoch Capabilities Index, by release date.