Falcon-7B
Falcon-7B.
19
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Technology Innovation Institute Apr 2023 Falcon-7B
Open weights
73.4
#245 of 256
Epoch Capabilities Index
- Open Arabic LLM Leaderboard v1 35% #55 /55
- IndoMMLU 25.1% #5 /5
- MedQA 25.4% #70 /71
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% | #30 of 63 | Claim in Falcon2-11B Technical Report, via Epoch AI | |
| LAMBADA | 74.9% | #13 of 26 | Claim in The Falcon Series of Open Language Models, via Epoch AI | |
| PIQA | 80.3% | #34 of 58 | Claim in The Falcon Series of Open Language Models, via Epoch AI | |
| OpenBookQA | 51.6% | #26 of 41 | Claim in Llama 2: Open Foundation and Fine-Tuned Chat Models, via Epoch AI | |
| ARC-Challenge | 47.9% | #48 of 75 | Claim in Falcon2-11B Technical Report, via Epoch AI | |
| WinoGrande | 67.2% | #54 of 76 | Claim in XGen-7B Technical Report, via Epoch AI | |
| BoolQ | 73.8% | #46 of 61 | Claim in The Falcon Series of Open Language Models, via Epoch AI | |
| MuSR | 37.8% | #74 of 98 | Official leaderboard | |
| TriviaQA | 64.6% | #32 of 38 | Claim in Llama 2: Open Foundation and Fine-Tuned Chat Models, via Epoch AI | |
| MMLU | 35% | #76 of 85 | Claim in Falcon2-11B Technical Report, via Epoch AI | |
| BIG-Bench Hard | 28.8% | #44 of 45 | Claim in Baichuan 2: Open Large-scale Language Models, via Epoch AI | |
| Open Arabic LLM Leaderboard v1 | 35% | #55 of 55 | Official leaderboard | |
| AlpacaEval 2.0 | 4.04% | #47 of 47 | Official leaderboard | |
| IndoMMLU | 25.1% | #5 of 5 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| GSM8K | 4.00% | #17 of 24 | Stanford HELM, via Epoch AI |
Professional work
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MedQA | 25.4% | #70 of 71 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| HELM Classic | 37.8 | #14 of 17 | Official leaderboard | |
| Open LLM Leaderboard v2 | 5.17 | #97 of 99 | 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.
Source: Epoch Capabilities Index, Epoch AI (CC BY 4.0)