Falcon-180B
Falcon-180B places in the top three on 2 benchmarks.
11
Benchmarks with a score
0
Ranked first, out of five or more models
2
In the top three
Falcon-180B
Open weights
112.0
#222 of 271
Epoch Capabilities Index
- LAMBADA 79.8% #3 /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 | 89% | #3 of 74 | Epoch AI | |
| WinoGrande | 87.1% | #4 of 76 | Epoch AI | |
| BoolQ | 89% | #6 of 75 | Epoch AI | |
| PIQA | 84.9% | #5 of 58 | Epoch AI | |
| LAMBADA | 79.8% | #3 of 26 | Epoch AI | |
| OpenBookQA | 64.2% | #12 of 41 | Epoch AI | |
| ARC-Challenge | 67.8% | #26 of 75 | Epoch AI | |
| MMLU | 70.6% | #53 of 127 | Epoch AI | |
| EQ-Bench v2 | 56.8 | #71 of 85 | Official leaderboard | |
| LMArena (Elo) | 1,148 | #307 of 333 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| GSM8K | 54.4% | #34 of 82 | Epoch AI |
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.